© 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. 45818
    Prev
    Next
    INDEX
    Explanations

    political and military-related terms and entities

    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
    +0.26
    1.2%
    565
    +0.11
    0.5%
    559
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.26
    0.29
    40
    +0.11
    0.12
    116
    +0.10
    0.07
    Negative Logits
    ashtra
    -0.71
     IPM
    -0.67
    sung
    -0.62
    ealous
    -0.61
     equival
    -0.60
     Hodg
    -0.59
    ouk
    -0.59
     Brach
    -0.59
    axter
    -0.58
    DEBUG
    -0.58
    POSITIVE LOGITS
    nings
    0.85
    stadt
    0.75
    papers
    0.69
     Rampage
    0.67
     Cinema
    0.66
    pac
    0.66
    fleet
    0.65
    models
    0.65
     Geo
    0.64
    izons
    0.62
    Activations Density 18.496%

    No Known Activations