© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 46066
    Prev
    Next
    INDEX
    Explanations

    mentions of political ideologies and leaders

    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
    520
    +0.11
    0.6%
    693
    +0.10
    0.5%
    24
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.11
    0.12
    701
    +0.10
    0.08
    639
    +0.08
    0.10
    Negative Logits
    eret
    -0.67
    hett
    -0.56
    hiba
    -0.56
    Downloadha
    -0.55
    afety
    -0.55
    ecause
    -0.55
    jri
    -0.54
    atche
    -0.54
    ogs
    -0.54
    accompan
    -0.54
    POSITIVE LOGITS
     Centauri
    0.68
    autical
    0.66
    omaly
    0.65
    wered
    0.62
    Ü
    0.59
    axis
    0.57
     Catalyst
    0.57
    âĶĢâĶĢâĶĢâĶĢ
    0.57
    enment
    0.53
    ALLY
    0.52
    Activations Density 6.150%

    No Known Activations