© 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. 10809
    Prev
    Next
    INDEX
    Explanations

    references to strong emotions or intense beliefs, particularly of a positive nature

    oai_token-act-pair · gpt-3.5-turbo

    expressions of enthusiasm and strong emotional commitment

    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
    avis
    -0.80
    ramid
    -0.77
    ©¶æ
    -0.77
    atu
    -0.75
    edu
    -0.74
    eon
    -0.71
    adr
    -0.68
    nih
    -0.68
    othy
    -0.68
    amn
    -0.68
    POSITIVE LOGITS
     passionate
    1.10
     passionately
    0.93
     passion
    0.82
    rament
    0.73
     applause
    0.72
     entreprene
    0.69
     upd
    0.67
     curiosity
    0.64
     exponent
    0.64
    itiz
    0.64
    Activations Density 0.011%

    No Known Activations