© 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. 9-RES-JB
    11. 1707
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to similarity or replication

    oai_token-act-pair · gpt-3.5-turbo

    instances of redundancy and similarity in language or technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -0.79
    ablishment
    -0.76
    bernatorial
    -0.73
    worthiness
    -0.68
    iferation
    -0.64
    essee
    -0.64
    én
    -0.64
    licts
    -0.63
    enegger
    -0.63
    owship
    -0.63
    POSITIVE LOGITS
     techniques
    1.09
     technique
    1.06
     methods
    1.00
     pronouns
    0.96
     pseudonym
    0.95
     tactics
    0.94
     terminology
    0.94
     sparing
    0.93
     tools
    0.93
     notation
    0.91
    Activations Density 0.342%

    No Known Activations