© 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. 3637
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency-related terms and technology-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to technology, brands, and health-related terms

    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
     counterpart
    -0.52
     lightly
    -0.51
     Dangerous
    -0.51
    APTER
    -0.50
    .--
    -0.50
     regards
    -0.48
     convenient
    -0.47
     following
    -0.47
     theirs
    -0.46
    agonist
    -0.45
    POSITIVE LOGITS
     etc
    1.02
    etc
    0.91
    whatever
    0.62
    ax
    0.59
    rote
    0.58
    ité
    0.56
    âĢ¦)
    0.56
    bra
    0.52
    romy
    0.51
    tek
    0.51
    Activations Density 0.534%

    No Known Activations