© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 3764
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a reliance or dependence on specific criteria or factors

    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
    242
    +0.14
    0.6%
    235
    +0.13
    0.6%
    400
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.14
    0.04
    400
    +0.13
    0.04
    714
    +0.12
    0.03
    Negative Logits
    OOD
    -0.86
    åħī
    -0.83
    äºĶ
    -0.82
    èª
    -0.81
    UES
    -0.81
    ACTED
    -0.81
    ãģ®å®
    -0.80
    ODY
    -0.80
    ARR
    -0.78
    ISH
    -0.77
    POSITIVE LOGITS
    cipled
    0.65
     hull
    0.62
     batch
    0.62
     absolutely
    0.59
     Chong
    0.58
     cement
    0.58
     iteration
    0.58
     scanners
    0.58
     Flyers
    0.58
     goddamn
    0.58
    Activations Density 0.367%

    No Known Activations