© 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. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4740
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "unique" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    99
    +0.10
    0.5%
    383
    +0.10
    0.5%
    663
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.10
    0.02
    99
    +0.10
    0.02
    623
    +0.10
    0.02
    Negative Logits
    ©¶æ
    -0.60
    à©
    -0.59
    EEE
    -0.58
    gone
    -0.58
    Īè
    -0.58
     Alive
    -0.56
     Mandatory
    -0.55
     overc
    -0.55
     Rae
    -0.55
     Suz
    -0.55
    POSITIVE LOGITS
     identifier
    1.13
     identifiers
    1.04
    ively
    1.02
    ties
    0.96
    ities
    0.93
    iates
    0.90
    iveness
    0.88
    arily
    0.84
     identifiable
    0.79
    iator
    0.78
    Activations Density 0.067%

    No Known Activations