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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7500
    Prev
    Next
    INDEX
    Explanations

    numerical information, particularly related to monetary amounts and contact details

    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
    +0.14
    0.6%
    495
    +0.12
    0.5%
    62
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    472
    +0.14
    0.02
    326
    +0.12
    0.02
    495
    +0.09
    0.02
    Negative Logits
     scrut
    -0.76
     enthusi
    -0.68
     horizont
    -0.66
     explan
    -0.65
     cradle
    -0.65
    onen
    -0.63
     misunder
    -0.62
    uca
    -0.60
     unforeseen
    -0.60
     reluct
    -0.60
    POSITIVE LOGITS
    00
    1.18
    86
    1.13
    84
    1.04
    87
    1.02
    63
    1.01
    93
    1.01
    50
    1.01
    81
    1.00
    70
    0.99
    82
    0.99
    Activations Density 0.085%

    No Known Activations