© 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. 23902
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic institutions, research, and professional titles

    oai_token-act-pair · gpt-3.5-turbo

    sentences that represent academic or professional affiliations

    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
     tremend
    -0.83
     sleeper
    -0.76
    !'"
    -0.70
     unlaw
    -0.66
     displeasure
    -0.66
     slightest
    -0.65
     challeng
    -0.65
     interference
    -0.65
     aven
    -0.64
     rematch
    -0.64
    POSITIVE LOGITS
     He
    1.23
     "[
    1.23
     "(
    1.19
     His
    1.16
     "
    1.09
     Previously
    1.06
     Though
    1.05
     Speaking
    1.03
     Essentially
    1.02
     "'
    1.02
    Activations Density 0.244%

    No Known Activations