© 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. 21359
    Prev
    Next
    INDEX
    Explanations

    personal statements or expressions of personal beliefs

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "be" and its variations

    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
    apter
    -0.87
    Rather
    -0.77
    mitter
    -0.76
    pmwiki
    -0.75
    farious
    -0.74
    ombat
    -0.74
    urst
    -0.73
    ãĤ´ãĥ³
    -0.72
    lude
    -0.70
    aru
    -0.70
    POSITIVE LOGITS
     also
    0.96
     gonna
    0.94
     gotta
    0.87
     ALSO
    0.80
     got
    0.77
     fuckin
    0.76
     definitely
    0.74
     furthermore
    0.73
     fucked
    0.72
     gotten
    0.72
    Activations Density 0.343%

    No Known Activations