© 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. 8-RES-JB
    11. 6426
    Prev
    Next
    INDEX
    Explanations

    statements prompting the reader to enjoy or appreciate something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Enjoy" and related phrases encouraging enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.78
    Enlarge
    -0.65
    mith
    -0.63
    ©¶æ
    -0.62
    staff
    -0.61
     detector
    -0.59
    Fact
    -0.59
     legion
    -0.58
    REF
    -0.58
    utm
    -0.57
    POSITIVE LOGITS
    ably
    0.92
    ances
    0.83
    joy
    0.79
    orable
    0.77
    able
    0.77
    lihood
    0.77
    nels
    0.76
    ivities
    0.75
    ables
    0.75
     Enjoy
    0.74
    Activations Density 0.033%

    No Known Activations