© 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. 3647
    Prev
    Next
    INDEX
    Explanations

    expressions related to negation and the concept of memory

    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
    446
    +0.10
    0.5%
    460
    +0.10
    0.4%
    559
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.10
    0.21
    446
    +0.10
    0.18
    183
    +0.10
    0.13
    Negative Logits
    door
    -0.68
    ARGET
    -0.68
     Greenwich
    -0.66
     2050
    -0.62
     sidx
    -0.61
     Rays
    -0.60
    WARD
    -0.60
    itatively
    -0.59
    avour
    -0.59
    represented
    -0.59
    POSITIVE LOGITS
     nor
    1.06
     anymore
    1.01
    £ı
    0.81
     anyways
    0.79
     Flavoring
    0.78
     :(
    0.75
     nonetheless
    0.75
    ħĭ
    0.73
     nevertheless
    0.71
     anyway
    0.70
    Activations Density 28.329%

    No Known Activations