© 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. 10-RES-JB
    11. 20366
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and symbols used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruck
    -0.69
    ocy
    -0.68
    oller
    -0.64
    oler
    -0.63
    ollower
    -0.62
    earch
    -0.60
    ior
    -0.60
    urry
    -0.60
    ousel
    -0.59
    iful
    -0.59
    POSITIVE LOGITS
    something
    1.09
    enough
    0.98
    albeit
    0.95
    perhaps
    0.93
     something
    0.92
    including
    0.90
     meaning
    0.89
    meaning
    0.88
    although
    0.83
    despite
    0.83
    Activations Density 0.123%

    No Known Activations