© 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. 10-RES-JB
    11. 24029
    Prev
    Next
    INDEX
    Explanations

    terms related to various forms of entertainment and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to fantasy or gaming elements involving mythical creatures and challenging environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.75
     exceptions
    -0.74
    ouple
    -0.67
    ItemTracker
    -0.67
     reluctance
    -0.66
    arently
    -0.64
     miscar
    -0.64
     objected
    -0.64
    FML
    -0.64
     declined
    -0.64
    POSITIVE LOGITS
     PLUS
    1.17
     effortlessly
    1.11
    !
    1.09
    eaturing
    1.04
     Featuring
    1.01
    !.
    0.96
     seamlessly
    0.95
    !!
    0.93
     featuring
    0.92
    !!!
    0.90
    Activations Density 0.668%

    No Known Activations