© 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. 4005
    Prev
    Next
    INDEX
    Explanations

    actions and indications of purpose or intention in the text

    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
    536
    +0.11
    0.5%
    494
    +0.11
    0.5%
    281
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    520
    +0.11
    0.05
    440
    +0.11
    0.05
    554
    +0.09
    0.06
    Negative Logits
    ãĤ´ãĥ³
    -0.74
    DAQ
    -0.73
     neutrality
    -0.70
     offerings
    -0.60
     affiliation
    -0.60
    Higher
    -0.60
     fixation
    -0.60
     affordability
    -0.59
    ajo
    -0.59
    ãĥīãĥ©ãĤ´ãĥ³
    -0.58
    POSITIVE LOGITS
    shed
    0.75
    wered
    0.75
    968
    0.74
    paces
    0.71
    ']
    0.70
    umat
    0.70
    remember
    0.68
    ickr
    0.67
    pload
    0.67
    ursed
    0.67
    Activations Density 0.818%

    No Known Activations