© 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. 3583
    Prev
    Next
    INDEX
    Explanations

    references to research studies and their methodologies

    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
    258
    +0.11
    0.5%
    269
    +0.10
    0.5%
    224
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.11
    0.05
    269
    +0.10
    0.04
    171
    +0.10
    0.04
    Negative Logits
     thirst
    -0.59
    aned
    -0.59
    zzy
    -0.58
     wearer
    -0.57
    hom
    -0.57
    nown
    -0.56
    ince
    -0.56
     possessing
    -0.56
     comprom
    -0.56
     Decay
    -0.56
    POSITIVE LOGITS
     Buckley
    0.75
     Aires
    0.74
    yssey
    0.69
    sonian
    0.67
    ope
    0.66
     Horowitz
    0.65
     ausp
    0.65
     ANGEL
    0.64
    BuyableInstoreAndOnline
    0.63
     Univ
    0.63
    Activations Density 0.730%

    No Known Activations