© 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. 4735
    Prev
    Next
    INDEX
    Explanations

    proper nouns, likely related to specific events, dates, or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to dates and numerical 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
     governed
    -0.85
     favour
    -0.84
     hydrogen
    -0.82
     disciplines
    -0.81
     quarterly
    -0.80
     greenhouse
    -0.80
     habitat
    -0.80
     furnace
    -0.79
     commissions
    -0.79
     disadvantage
    -0.78
    POSITIVE LOGITS
    RIP
    1.84
    @
    1.83
    Looks
    1.79
    Wow
    1.71
    https
    1.68
    Cong
    1.65
    BRE
    1.65
    Others
    1.62
    Dear
    1.60
    Apparently
    1.59
    Activations Density 0.229%

    No Known Activations