© 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. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 4874
    Prev
    Next
    INDEX
    Explanations

    phrases indicating progress or attainment of levels

    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
    608
    +0.13
    0.6%
    218
    +0.12
    0.6%
    43
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    183
    +0.13
    0.03
    761
    +0.12
    0.04
    604
    +0.10
    0.03
    Negative Logits
    wcsstore
    -0.67
     includ
    -0.66
     EVENTS
    -0.66
     alone
    -0.65
     gladly
    -0.61
    handler
    -0.61
    hair
    -0.60
    gay
    -0.60
    soever
    -0.58
    comings
    -0.58
    POSITIVE LOGITS
     saturation
    1.06
     puberty
    1.05
     maturity
    0.96
     exhaustion
    0.95
     adulthood
    0.94
     adolescence
    0.93
     parity
    0.92
     equilibrium
    0.90
     climax
    0.88
     boiling
    0.81
    Activations Density 0.180%

    No Known Activations