© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5255
    Prev
    Next
    INDEX
    Explanations

    street addresses or location-related terms

    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
    373
    +0.19
    0.9%
    504
    +0.10
    0.5%
    247
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.19
    0.03
    325
    +0.10
    0.02
    145
    +0.10
    0.02
    Negative Logits
     herds
    -0.78
    icter
    -0.76
     traditions
    -0.72
     arsen
    -0.69
    put
    -0.69
    ozy
    -0.66
     nurse
    -0.65
     medicines
    -0.64
     rhythms
    -0.63
     fleets
    -0.63
    POSITIVE LOGITS
     Suite
    0.95
     NW
    0.92
    Philadelphia
    0.80
    irez
    0.75
     SW
    0.72
    NW
    0.71
    Houston
    0.68
    .,
    0.67
    SW
    0.65
     rgb
    0.65
    Activations Density 0.084%

    No Known Activations