© 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. 9-RES-JB
    11. 3676
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe qualities or states

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that convey varying degrees of intensity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thood
    -0.85
    arest
    -0.80
    fresh
    -0.77
    verage
    -0.76
    leaf
    -0.75
    ighter
    -0.75
    redits
    -0.75
    earchers
    -0.75
    Launch
    -0.74
    entimes
    -0.73
    POSITIVE LOGITS
     sounding
    1.00
     undertaking
    0.86
     (>
    0.85
     dataset
    0.85
     situation
    0.85
     task
    0.83
     proposition
    0.83
     scenario
    0.81
     thing
    0.79
     topic
    0.78
    Activations Density 0.276%

    No Known Activations