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. 9-RES-JB
    6. 12105
    Prev
    Next
    INDEX
    Explanations

    a specific naming pattern involving a mix of names and initials ending with symbols

    oai_token-act-pair · gpt-3.5-turbo

    specific formats or structural elements in data or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ich
    -0.75
    etus
    -0.68
    */(
    -0.66
     Asuka
    -0.65
    atl
    -0.64
     Eyes
    -0.64
     Coca
    -0.64
     Ghosts
    -0.64
     appendix
    -0.64
     IST
    -0.63
    POSITIVE LOGITS
    R
    1.31
    r
    1.31
    ron
    1.18
    rin
    1.15
    rs
    1.14
    RB
    1.12
     Ri
    1.12
    ri
    1.12
    RP
    1.12
    ra
    1.11
    Activations Density 0.474%

    No Known Activations