© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17108
    Prev
    Next
    INDEX
    Explanations

    references to the name "Joss" with varying levels of importance or relevance

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Goss" and related references

    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
    ãĥ£
    -0.72
    ufact
    -0.71
    è¦ļéĨĴ
    -0.67
    ropolitan
    -0.63
    assies
    -0.61
    abolic
    -0.61
    senal
    -0.58
    Beast
    -0.58
    mate
    -0.58
    ancial
    -0.56
    POSITIVE LOGITS
     Whedon
    1.22
    essing
    1.02
    essed
    0.97
    es
    0.94
    edIn
    0.92
    ips
    0.90
    essor
    0.89
    essors
    0.88
    enger
    0.88
    yne
    0.87
    Activations Density 0.013%

    No Known Activations