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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 18640
    Prev
    Next
    INDEX
    Explanations

    phrases related to observations or analysis of performance or behavior

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "look" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.77
    ipl
    -0.75
     remem
    -0.67
     Reporting
    -0.65
     Details
    -0.65
     Clicker
    -0.63
    orb
    -0.62
    orf
    -0.59
    ference
    -0.59
    $$$$
    -0.58
    POSITIVE LOGITS
     poised
    1.09
     unstoppable
    0.99
     primed
    0.95
     shaky
    0.94
     bullish
    0.84
     vulnerable
    0.84
     destined
    0.83
     unbeat
    0.83
     increasingly
    0.82
     likely
    0.81
    Activations Density 0.048%

    No Known Activations