© 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. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 3851
    Prev
    Next
    INDEX
    Explanations

    phrases related to the usage of substances or items in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.3.hook_attn_out
    Hook Layer
    3
    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
    432
    +0.09
    0.4%
    713
    +0.08
    0.4%
    558
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.09
    0.04
    206
    +0.08
    0.03
    341
    +0.08
    0.04
    Negative Logits
    ega
    -0.79
    HK
    -0.74
    atform
    -0.72
    dev
    -0.72
    UTERS
    -0.69
    Camera
    -0.68
    conv
    -0.67
    cients
    -0.66
    itte
    -0.66
    otta
    -0.66
    POSITIVE LOGITS
     MW
    0.73
     Ames
    0.72
    amph
    0.71
     Gators
    0.70
     ALEC
    0.66
     Tate
    0.65
    aukee
    0.64
     AFL
    0.64
     Mankind
    0.63
     Kamp
    0.63
    Activations Density 0.255%

    No Known Activations