© 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. 3522
    Prev
    Next
    INDEX
    Explanations

    phrases related to fundraising activities and events

    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
    +0.26
    1.2%
    373
    +0.13
    0.6%
    459
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    218
    +0.26
    0.21
    173
    +0.13
    0.13
    666
    +0.12
    0.08
    Negative Logits
     Converted
    -0.69
    apter
    -0.67
    urated
    -0.67
     Inher
    -0.64
     Allows
    -0.63
    veland
    -0.60
    ozyg
    -0.60
     Presbyterian
    -0.59
     reinstated
    -0.58
     inherited
    -0.57
    POSITIVE LOGITS
     scrut
    0.81
     Guinness
    0.68
     arrang
    0.66
     afore
    0.66
     unbeliev
    0.66
    yss
    0.65
     anonymity
    0.65
     confidentiality
    0.64
    mentioned
    0.63
    ISIS
    0.62
    Activations Density 17.707%

    No Known Activations