© 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. 6031
    Prev
    Next
    INDEX
    Explanations

    phrases expressing hope or optimism

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing hope or expectations about future outcomes

    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
    ocaust
    -0.79
    idelines
    -0.78
    TN
    -0.74
    vil
    -0.73
    wn
    -0.70
    ulu
    -0.70
    IGN
    -0.70
    AKING
    -0.69
    ãĤ´ãĥ³
    -0.69
    elfare
    -0.69
    POSITIVE LOGITS
     someday
    1.17
     whoever
    0.74
    eday
    0.72
     they
    0.68
     future
    0.67
     someone
    0.67
     inexperienced
    0.65
     sooner
    0.63
    cher
    0.63
     arose
    0.62
    Activations Density 0.130%

    No Known Activations