© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1138
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating involvement or inclusion within a certain group, plan, or historical context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.33
    1.1%
    362
    +0.16
    0.5%
    211
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.33
    0.06
    172
    +0.16
    0.06
    84
    +0.13
    0.04
    Negative Logits
    acs
    -1.12
    ebted
    -1.01
    culosis
    -0.96
    ians
    -0.93
    rimp
    -0.93
    ants
    -0.92
     conduc
    -0.91
    jobs
    -0.85
    ancies
    -0.85
    lean
    -0.83
    POSITIVE LOGITS
     larger
    0.91
    lined
    0.91
    ICLE
    0.90
     bounds
    0.89
     the
    0.87
     everyday
    0.87
     society
    0.87
    lining
    0.87
     Mine
    0.86
     UNESCO
    0.86
    Activations Density 0.910%

    No Known Activations