© 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. 12740
    Prev
    Next
    INDEX
    Explanations

    phrases related to motives or reasons for actions

    oai_token-act-pair · gpt-3.5-turbo

    arguments related to motivations and reasons behind decisions or actions

    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
    isode
    -0.92
    iard
    -0.90
    »Ĵ
    -0.90
    elta
    -0.87
    byter
    -0.81
    inis
    -0.77
    Cover
    -0.75
    ÙĴ
    -0.75
    enaries
    -0.75
    代
    -0.74
    POSITIVE LOGITS
     sheer
    1.38
     inexper
    1.37
     curiosity
    1.35
     nostalgia
    1.35
     impat
    1.30
     jealousy
    1.29
     boredom
    1.28
     desire
    1.27
     ignorance
    1.26
     fear
    1.26
    Activations Density 0.324%

    No Known Activations