© 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. 4064
    Prev
    Next
    INDEX
    Explanations

    capitalized words related to abbreviations or acronyms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "GL" and variations of it in different contexts

    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
    stood
    -1.01
    zynski
    -0.69
    ricular
    -0.68
    chers
    -0.67
    cient
    -0.67
    Rated
    -0.64
    ItemTracker
    -0.63
    taining
    -0.62
    nai
    -0.61
    eers
    -0.61
    POSITIVE LOGITS
    ength
    1.12
    asses
    1.00
    ibrary
    0.96
    adiator
    0.91
    ogue
    0.84
    igion
    0.82
    ossip
    0.80
    ocal
    0.80
    obe
    0.80
    eston
    0.79
    Activations Density 0.049%

    No Known Activations