© 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. 3-RES-JB
    11. 15092
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of media content such as TV shows, movies, and music

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with entertainment and pop culture references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Iraq
    -0.57
     Prosecut
    -0.56
     IRA
    -0.54
    ossier
    -0.54
     militias
    -0.53
    Federal
    -0.52
     segregated
    -0.51
    isman
    -0.51
     subsistence
    -0.50
    tein
    -0.50
    POSITIVE LOGITS
     Uncharted
    0.64
    nown
    0.60
     Anime
    0.59
     Robot
    0.59
     Morty
    0.59
     droid
    0.57
     sci
    0.57
     Remix
    0.56
     LEGO
    0.55
     anime
    0.55
    Activations Density 2.888%

    No Known Activations