© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9375
    Prev
    Next
    INDEX
    Explanations

    words related to various activities like rap, dancing, and events

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or shortened forms of words in various contexts

    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
     upside
    -0.62
     disenfranch
    -0.61
     Wales
    -0.60
     omission
    -0.60
     Dane
    -0.56
     prized
    -0.56
     lik
    -0.55
     quantity
    -0.55
    OWS
    -0.55
    #$
    -0.54
    POSITIVE LOGITS
    monary
    1.04
    incial
    0.86
    rha
    0.84
    ophe
    0.84
    apa
    0.83
    oe
    0.82
    ilon
    0.79
    itive
    0.79
    ocry
    0.77
    athy
    0.77
    Activations Density 0.142%

    No Known Activations