© 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. 3930
    Prev
    Next
    INDEX
    Explanations

    terms related to cows and their associations 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
    218
    +0.15
    0.7%
    354
    +0.10
    0.5%
    297
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.15
    0.01
    371
    +0.10
    0.01
    403
    +0.10
    0.01
    Negative Logits
    achev
    -0.83
    ģ«
    -0.76
    cape
    -0.68
    href
    -0.67
    kaya
    -0.67
    omnia
    -0.65
    Downloadha
    -0.65
    paralle
    -0.65
    ensional
    -0.64
     amen
    -0.62
    POSITIVE LOGITS
     asses
    0.71
    aneers
    0.67
     Australians
    0.65
    orative
    0.62
     Goose
    0.62
    TAG
    0.62
    ESE
    0.61
    estern
    0.60
     pigs
    0.60
     Rye
    0.58
    Activations Density 0.075%

    No Known Activations