© 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. 8-RES-JB
    11. 16746
    Prev
    Next
    INDEX
    Explanations

    assertive statements about individuals' knowledge or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that initiate clauses with "anyone who" or similar structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anonymity
    -0.67
    anmar
    -0.67
     Recovery
    -0.67
    urrection
    -0.64
     ultras
    -0.64
    urers
    -0.63
     SAS
    -0.62
    ranging
    -0.58
     Medals
    -0.56
    united
    -0.56
    POSITIVE LOGITS
     knows
    1.00
    pires
    1.00
     subscrib
    0.95
    soever
    0.91
    ever
    0.87
     willfully
    0.86
     entert
    0.84
     understands
    0.84
     possesses
    0.84
     ever
    0.83
    Activations Density 0.106%

    No Known Activations