© 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. 14163
    Prev
    Next
    INDEX
    Explanations

    feelings or emotions in text

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotions or feelings

    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
    cedes
    -0.80
    afort
    -0.72
    annis
    -0.69
    nect
    -0.69
    itors
    -0.66
    wald
    -0.66
    estyles
    -0.65
    umbn
    -0.65
    aciously
    -0.65
     Cosponsors
    -0.63
    POSITIVE LOGITS
     that
    0.86
     sympathy
    0.80
     of
    0.80
     feeling
    0.76
     sadness
    0.75
     satisfaction
    0.72
     compulsion
    0.72
     impression
    0.71
     inev
    0.71
     enthusi
    0.70
    Activations Density 0.076%

    No Known Activations