© 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. 6-RES-JB
    11. 24456
    Prev
    Next
    INDEX
    Explanations

    dates written in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    specific types of punctuation and structural elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heastern
    -0.62
     faiths
    -0.61
    ervatives
    -0.60
    venants
    -0.59
    tsy
    -0.58
    anty
    -0.57
     disadvantaged
    -0.56
     departments
    -0.56
    cipl
    -0.56
     professions
    -0.56
    POSITIVE LOGITS
    ciation
    0.73
     {*
    0.65
    Async
    0.62
     titled
    0.62
    ļé
    0.61
    xxxxxxxx
    0.61
    was
    0.59
    sets
    0.57
     headlined
    0.57
     yours
    0.57
    Activations Density 1.007%

    No Known Activations