© 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. 5269
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to technology and the film industry

    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
    526
    +0.12
    0.6%
    373
    +0.11
    0.5%
    365
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.02
    343
    +0.11
    0.01
    709
    +0.10
    0.01
    Negative Logits
    ITIES
    -0.71
    RAFT
    -0.71
    OGR
    -0.71
     Lauder
    -0.66
    Leary
    -0.65
     impunity
    -0.65
     eleph
    -0.64
     DRAG
    -0.62
     ratios
    -0.62
    hips
    -0.62
    POSITIVE LOGITS
    Bridge
    0.85
    asus
    0.84
    ãĥĥ
    0.82
    fork
    0.81
    phony
    0.76
    record
    0.74
    audio
    0.74
    ctl
    0.73
    cert
    0.73
    cia
    0.73
    Activations Density 0.058%

    No Known Activations