© 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. 7680
    Prev
    Next
    INDEX
    Explanations

    single uppercase letters or acronyms in a particular context

    oai_token-act-pair · gpt-3.5-turbo

    capital letters or proper nouns

    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
    )=(
    -0.79
    hire
    -0.78
    bent
    -0.73
    xon
    -0.73
    negie
    -0.72
    REDACTED
    -0.67
    come
    -0.64
    crim
    -0.64
    orio
    -0.64
    bring
    -0.63
    POSITIVE LOGITS
    umps
    0.94
    ucks
    0.85
    ippers
    0.82
    oses
    0.79
    ixture
    0.78
    enses
    0.77
    umper
    0.76
    leep
    0.75
    agging
    0.75
    oots
    0.74
    Activations Density 0.149%

    No Known Activations