© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29022
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negative emotions or criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    720
    +0.13
    0.6%
    373
    +0.12
    0.6%
    640
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.13
    0.07
    297
    +0.12
    0.05
    546
    +0.12
    0.04
    Negative Logits
    ously
    -0.79
    orts
    -0.65
    xes
    -0.59
    veland
    -0.57
    .):
    -0.57
    rette
    -0.57
    ?:
    -0.56
    /(
    -0.55
    :[
    -0.53
    Initialized
    -0.53
    POSITIVE LOGITS
    _-
    1.70
    especially
    1.09
    although
    1.02
    they
    0.99
    particularly
    0.98
     namely
    0.95
    unless
    0.94
     ie
    0.94
    perhaps
    0.93
    except
    0.93
    Activations Density 0.240%

    No Known Activations