© 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. 3735
    Prev
    Next
    INDEX
    Explanations

    instances of problem-solving and attempts to address challenges

    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
    689
    +0.10
    0.5%
    142
    +0.10
    0.4%
    84
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    221
    +0.10
    0.04
    255
    +0.10
    0.11
    689
    +0.09
    0.07
    Negative Logits
    Commerce
    -0.68
    olitical
    -0.66
    ramid
    -0.66
     appointed
    -0.66
    teenth
    -0.63
     Governors
    -0.62
    )?
    -0.61
    ages
    -0.60
     annexed
    -0.59
    pled
    -0.59
    POSITIVE LOGITS
    onite
    0.86
    sylv
    0.73
     pel
    0.71
     buggy
    0.70
     unden
    0.68
    oxic
    0.68
     conflic
    0.68
     fail
    0.67
     Mub
    0.65
     succeed
    0.64
    Activations Density 8.037%

    No Known Activations