© 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. 4-RES-JB
    11. 397
    Prev
    Next
    INDEX
    Explanations

    numeric patterns that end with a word

    oai_token-act-pair · gpt-3.5-turbo

    references to first-year experiences or first occurrences in various contexts

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

    No Comments

    Negative Logits
     unfocusedRange
    -0.83
    tnc
    -0.77
    ulkan
    -0.73
    interrupted
    -0.73
    tools
    -0.67
    Spoiler
    -0.67
    ingen
    -0.65
    rible
    -0.64
    uts
    -0.63
     tremend
    -0.63
    POSITIVE LOGITS
     introdu
    0.72
     whiff
    0.71
     foremost
    0.67
     Rouhani
    0.66
    imester
    0.66
    endment
    0.64
    enium
    0.62
    ISA
    0.62
     Centauri
    0.61
     foray
    0.61
    Activations Density 0.196%

    No Known Activations