© 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. 14885
    Prev
    Next
    INDEX
    Explanations

    words related to music and art, especially focusing on "fireside stories" and "ranch."

    oai_token-act-pair · gpt-3.5-turbo

    references to storytelling and music-related themes

    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
    BIP
    -0.66
    ammers
    -0.62
    ETF
    -0.60
    etsk
    -0.60
    lihood
    -0.60
    debian
    -0.59
    Reg
    -0.58
    ebus
    -0.58
     preventive
    -0.58
    akeru
    -0.57
    POSITIVE LOGITS
     rave
    0.74
     backstage
    0.71
     acclaim
    0.70
     fame
    0.69
     Illustrated
    0.64
     onstage
    0.63
     paperback
    0.62
     circa
    0.62
    nown
    0.61
     fetish
    0.61
    Activations Density 1.525%

    No Known Activations