© 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. 3563
    Prev
    Next
    INDEX
    Explanations

    financial terminology and specific numerical data related to costs and expenses

    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
    497
    +0.25
    1.2%
    459
    +0.16
    0.7%
    685
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.25
    -0.03
    151
    +0.16
    0.16
    404
    +0.10
    0.09
    Negative Logits
    autions
    -0.68
    erity
    -0.67
    OLOGY
    -0.66
    WARD
    -0.66
    ¶
    -0.66
    IRC
    -0.65
     Quit
    -0.65
    internet
    -0.65
     Osw
    -0.65
    umblr
    -0.64
    POSITIVE LOGITS
     centrif
    0.71
     displacement
    0.69
     latt
    0.68
     vacuum
    0.65
    chlor
    0.63
    isable
    0.63
     suspension
    0.61
    enfranch
    0.59
     ignition
    0.59
     pace
    0.59
    Activations Density 11.611%

    No Known Activations