© 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. 39986
    Prev
    Next
    INDEX
    Explanations

    mentions of the color 'black'

    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
    447
    +0.23
    0.9%
    70
    +0.14
    0.5%
    12
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.23
    0.09
    12
    +0.14
    0.06
    365
    +0.13
    0.04
    Negative Logits
    PsyNetMessage
    -1.17
    ablishment
    -1.06
    igslist
    -1.04
    OPLE
    -1.00
    ICLE
    -0.95
    mble
    -0.94
    ixel
    -0.93
    oldemort
    -0.88
    rative
    -0.88
     Lauder
    -0.88
    POSITIVE LOGITS
    smith
    1.47
    jack
    1.37
    berry
    1.28
    ened
    1.24
    bird
    1.20
    hawk
    1.19
    moon
    1.11
    horse
    1.08
    berries
    1.05
    powder
    1.04
    Activations Density 6.188%

    No Known Activations