Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 8113
    Prev
    Next
    INDEX
    Explanations

    YouTube video links

    oai_token-act-pair · gpt-3.5-turbo

    YouTube links and references

    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
     Gillespie
    -0.68
    omez
    -0.68
     Midlands
    -0.63
     Pence
    -0.63
    uala
    -0.63
     Adelaide
    -0.63
     Metro
    -0.63
    thia
    -0.62
    livious
    -0.62
     Ballard
    -0.61
    POSITIVE LOGITS
    youtu
    1.15
    watch
    1.12
    youtube
    0.92
     Seen
    0.79
     WATCHED
    0.77
     Traps
    0.76
    çīĪ
    0.75
    :/
    0.74
     Plays
    0.71
    uploads
    0.71
    Activations Density 0.009%

    No Known Activations