© 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. 0-RES-JB
    11. 22297
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong opinions or endorsements

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong belief or conviction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mares
    -0.71
    chen
    -0.65
    amac
    -0.64
     Endless
    -0.64
    ufact
    -0.63
    Crew
    -0.62
    ogue
    -0.61
    money
    -0.61
     Camer
    -0.61
    psons
    -0.60
    POSITIVE LOGITS
     strongly
    3.48
     vehemently
    1.84
     vigorously
    1.75
     passionately
    1.72
     firmly
    1.68
     powerfully
    1.63
     sharply
    1.63
     fiercely
    1.60
     deeply
    1.56
     heavily
    1.53
    Activations Density 0.010%

    No Known Activations