© 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. 7716
    Prev
    Next
    INDEX
    Explanations

    phrases related to extensive coverage and distribution

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "the" in various 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
    fully
    -0.79
    resy
    -0.70
    ful
    -0.67
    aba
    -0.67
    berus
    -0.66
    Edited
    -0.63
    arten
    -0.61
    TEXTURE
    -0.61
    User
    -0.61
    clair
    -0.60
    POSITIVE LOGITS
     globe
    1.04
     countryside
    1.00
     corners
    0.95
     world
    0.90
     place
    0.86
     country
    0.85
     damn
    0.83
     rooft
    0.83
     godd
    0.83
     scenery
    0.82
    Activations Density 0.063%

    No Known Activations