© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 9367
    Prev
    Next
    INDEX
    Explanations

    academic and research-related terms and activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to studies and analyses of data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Stretch
    -0.78
    ":[
    -0.78
    éģ
    -0.78
    bard
    -0.77
    Metal
    -0.73
    lings
    -0.71
    RAY
    -0.70
    Anyway
    -0.70
    Debug
    -0.70
    Task
    -0.69
    POSITIVE LOGITS
     trends
    1.17
     attitudes
    1.14
     perceptions
    1.00
     how
    0.96
     responses
    0.96
     whether
    0.92
     respondents
    0.91
     associations
    0.90
     prevalence
    0.86
     correlations
    0.85
    Activations Density 0.205%

    No Known Activations