Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 33247
    Prev
    Next
    INDEX
    Explanations

    names of cities, states, and people's names

    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
    188
    +0.14
    0.6%
    700
    +0.14
    0.6%
    659
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.18
    232
    +0.14
    0.17
    373
    +0.13
    -0.10
    Negative Logits
     envy
    -0.79
     coli
    -0.77
     ambassadors
    -0.73
     Pathfinder
    -0.72
     undecided
    -0.72
     alleg
    -0.72
     apex
    -0.70
     whales
    -0.70
     hindsight
    -0.69
     markup
    -0.69
    POSITIVE LOGITS
     Jr
    1.27
    ovich
    1.21
    owski
    1.18
    akis
    1.16
    orst
    1.15
    chuk
    1.14
    owicz
    1.13
    inski
    1.13
    opoulos
    1.11
    ansky
    1.10
    Activations Density 4.346%

    No Known Activations