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. 23359
    Prev
    Next
    INDEX
    Explanations

    references to music albums and songs

    oai_token-act-pair · gpt-3.5-turbo

    titles of songs, movies, or literary works

    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
    etheless
    -0.72
    theless
    -0.68
    intendent
    -0.60
     capacities
    -0.56
    cellaneous
    -0.55
     waived
    -0.55
     chem
    -0.54
     referen
    -0.52
     anecd
    -0.52
    userc
    -0.51
    POSITIVE LOGITS
     Guys
    0.73
     Daddy
    0.68
     Boys
    0.65
     Club
    0.64
     Collection
    0.64
     Remix
    0.63
     Machine
    0.60
     Balls
    0.59
     Festival
    0.59
     Circus
    0.59
    Activations Density 0.739%

    No Known Activations