© 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. 9843
    Prev
    Next
    INDEX
    Explanations

    phrases related to making arguments or claims

    oai_token-act-pair · gpt-3.5-turbo

    arguments and claims presented in a discussion

    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
    FORMATION
    -0.67
    PER
    -0.66
    Charges
    -0.62
     Brooks
    -0.62
    DER
    -0.59
    TPS
    -0.59
    KB
    -0.57
     offenses
    -0.57
    FORM
    -0.57
     rows
    -0.57
    POSITIVE LOGITS
    uably
    1.34
    uments
    1.08
    emouth
    1.08
    roup
    1.07
    rave
    1.07
    entin
    1.03
    raph
    1.02
    allery
    1.00
    arin
    0.99
    regate
    0.97
    Activations Density 0.034%

    No Known Activations