© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4966
    Prev
    Next
    INDEX
    Explanations

    mentions of "capacity" or related terms indicating the ability or potential to do something

    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
    288
    +0.12
    0.6%
    61
    +0.10
    0.5%
    161
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.02
    724
    +0.10
    0.02
    509
    +0.10
    0.01
    Negative Logits
    aida
    -0.80
    scene
    -0.71
    roma
    -0.71
    cause
    -0.66
    lique
    -0.64
     Surv
    -0.61
    dash
    -0.61
    WAR
    -0.60
    ation
    -0.60
    enthal
    -0.59
    POSITIVE LOGITS
     capacities
    1.05
     utilization
    0.94
     capacity
    0.91
    acity
    0.85
     Capacity
    0.78
    ibilities
    0.76
    abilities
    0.74
     gaps
    0.72
    ful
    0.71
    Reviewer
    0.70
    Activations Density 0.072%

    No Known Activations