© 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. 0-RES-JB
    11. 3386
    Prev
    Next
    INDEX
    Explanations

    Asian characters and potential names or titles within blocks of text, with a focus on words with unique characters and sequences within them

    oai_token-act-pair · gpt-3.5-turbo

    references to competitive placements or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ividual
    -0.77
    ecause
    -0.62
     ItemLevel
    -0.61
    ogun
    -0.61
    onga
    -0.59
    olean
    -0.56
    wark
    -0.54
    ocamp
    -0.54
    him
    -0.53
    ruary
    -0.52
    POSITIVE LOGITS
     antioxid
    0.91
     Seym
    0.82
    natureconservancy
    0.77
    Balt
    0.77
    ß
    0.77
     tradem
    0.75
     millenn
    0.75
    âĹ¼
    0.75
    PDATE
    0.73
    kefeller
    0.72
    Activations Density 2.687%

    No Known Activations