© 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. 7315
    Prev
    Next
    INDEX
    Explanations

    expressions of satisfaction or pride

    oai_token-act-pair · gpt-3.5-turbo

    expressions of pride and satisfaction

    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
    soever
    -0.72
    soDeliveryDate
    -0.71
    opus
    -0.69
    ictionary
    -0.67
    MRI
    -0.66
    fman
    -0.64
    odder
    -0.63
    nsic
    -0.63
    aque
    -0.62
    idious
    -0.62
    POSITIVE LOGITS
     how
    1.15
     what
    0.98
     having
    0.76
    what
    0.73
     whats
    0.73
     course
    0.73
     ourselves
    0.72
     whether
    0.71
    how
    0.71
     their
    0.70
    Activations Density 0.164%

    No Known Activations