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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 72
    Prev
    Next
    INDEX
    Explanations

    phrases related to construction and building

    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
    +0.28
    1.1%
    167
    +0.13
    0.5%
    578
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.28
    0.11
    362
    +0.13
    0.10
    36
    +0.11
    0.11
    Negative Logits
    mong
    -0.83
    onse
    -0.79
    peed
    -0.78
    enance
    -0.77
    doing
    -0.75
    words
    -0.74
    fulness
    -0.73
    seekers
    -0.73
    wash
    -0.72
    esson
    -0.72
    POSITIVE LOGITS
     new
    1.03
     makeshift
    0.97
     viable
    0.89
    irl
    0.86
    aganda
    0.82
    ural
    0.82
     safe
    0.82
     rudimentary
    0.82
     entire
    0.81
    urally
    0.80
    Activations Density 2.013%

    No Known Activations