© 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. 603
    Prev
    Next
    INDEX
    Explanations

    phrases expressing contrasting ideas

    oai_token-act-pair · gpt-3.5-turbo

    contradictory statements or contrasting information

    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
    ammed
    -0.71
    lement
    -0.67
    ISH
    -0.65
    HOU
    -0.63
    =>
    -0.62
    HAM
    -0.62
    irk
    -0.61
    legate
    -0.59
    lein
    -0.59
    assian
    -0.59
    POSITIVE LOGITS
     none
    1.36
     mostly
    1.23
     ultimately
    1.17
     chiefly
    1.16
     generally
    1.15
     overall
    1.14
     mainly
    1.13
     nothing
    1.12
     invariably
    1.06
     principally
    1.00
    Activations Density 0.245%

    No Known Activations