© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5612
    Prev
    Next
    INDEX
    Explanations

    words associated with political factions and organized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    581
    +0.12
    0.5%
    341
    +0.10
    0.5%
    71
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.09
    575
    +0.10
    0.08
    51
    +0.09
    0.07
    Negative Logits
    eka
    -0.62
    entimes
    -0.62
    hua
    -0.62
    ahime
    -0.61
    resy
    -0.60
    uristic
    -0.59
    iframe
    -0.58
    qus
    -0.58
     sometimes
    -0.57
    senal
    -0.57
    POSITIVE LOGITS
     except
    1.58
     imaginable
    1.44
    except
    1.13
     conceivable
    0.88
    Except
    0.87
    soever
    0.85
     simultaneously
    0.85
     Including
    0.84
     whatsoever
    0.82
     including
    0.80
    Activations Density 0.793%

    No Known Activations