© 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. 40374
    Prev
    Next
    INDEX
    Explanations

    details related to natural disasters and health concerns

    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
    +0.07
    0.7%
    218
    +0.06
    0.6%
    393
    +0.06
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.07
    0.01
    616
    +0.06
    0.09
    746
    +0.06
    0.04
    Negative Logits
    arta
    -0.34
    onto
    -0.30
    arily
    -0.29
    unts
    -0.28
     Taxes
    -0.28
     athlet
    -0.28
    ribe
    -0.28
    2019
    -0.28
    ike
    -0.27
    icles
    -0.26
    POSITIVE LOGITS
    cffffcc
    0.32
     murm
    0.31
     uproar
    0.30
     plenty
    0.30
    DAQ
    0.30
     rumours
    0.29
     vigorous
    0.29
     concerted
    0.29
     outcry
    0.29
     whispers
    0.29
    Activations Density 7.856%

    No Known Activations