© 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 Local
    9. 6-RES_SCL-AJT
    11. 4022
    Prev
    Next
    INDEX
    Explanations

    organizations and government topics related to monetary value and political figures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    195
    +0.18
    0.8%
    635
    +0.12
    0.5%
    285
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.25
    288
    +0.12
    0.24
    442
    +0.12
    0.10
    Negative Logits
    angular
    -0.89
    gdala
    -0.84
    onut
    -0.84
    oing
    -0.83
    esis
    -0.83
    heast
    -0.82
    oman
    -0.81
    service
    -0.81
    oway
    -0.80
    ĨĴ
    -0.80
    POSITIVE LOGITS
    thal
    0.82
    Reply
    0.76
    >>>>>>>>
    0.76
    ukemia
    0.66
    \\\\\\\\\\\\\\\\
    0.65
    Bron
    0.62
    haar
    0.61
     exch
    0.61
    ;;;;;;;;;;;;
    0.61
     Chimera
    0.59
    Activations Density 8.507%

    No Known Activations