© 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. 4-RES-JB
    11. 15421
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a break in content or a continuation of a story

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases indicating ongoing content or references to advertisements

    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
    bags
    -0.78
    RAW
    -0.72
    bag
    -0.64
    MM
    -0.63
     Compan
    -0.62
     Gujar
    -0.59
    Lens
    -0.59
    ointed
    -0.58
     Grimoire
    -0.58
     Integ
    -0.58
    POSITIVE LOGITS
     Thumbnails
    0.87
     trending
    0.75
    ideshow
    0.74
    imeo
    0.73
    ettings
    0.72
     gallery
    0.68
    tics
    0.67
    ient
    0.66
    ebin
    0.63
    perature
    0.63
    Activations Density 0.011%

    No Known Activations