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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 10827
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases related to organizing actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases with the word "at" indicating timing or specific moments

    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
     benefited
    -0.71
    eria
    -0.69
    gans
    -0.67
    vere
    -0.67
    uph
    -0.64
    biased
    -0.59
    Shell
    -0.59
    USA
    -0.58
    spective
    -0.58
    hash
    -0.58
    POSITIVE LOGITS
     least
    1.28
     halftime
    0.97
     sunset
    0.95
     times
    0.93
    roph
    0.91
    las
    0.90
     dusk
    0.88
    onement
    0.87
     intervals
    0.86
     midday
    0.84
    Activations Density 0.183%

    No Known Activations