© 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. 22346
    Prev
    Next
    INDEX
    Explanations

    adjectives related to physical height

    oai_token-act-pair · gpt-3.5-turbo

    references to varying levels of achievement or status

    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
    activ
    -0.74
    mod
    -0.69
    OC
    -0.66
    igil
    -0.64
    wed
    -0.63
    invoke
    -0.62
    spoken
    -0.61
     Restore
    -0.61
    eret
    -0.60
     spare
    -0.59
    POSITIVE LOGITS
     heights
    4.54
     depths
    1.76
     height
    1.51
     Heights
    1.45
     highs
    1.45
     slopes
    1.43
     lengths
    1.40
     extremes
    1.36
     lows
    1.30
     distances
    1.30
    Activations Density 0.018%

    No Known Activations