© 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. 9890
    Prev
    Next
    INDEX
    Explanations

    implicit or tacit references

    oai_token-act-pair · gpt-3.5-turbo

    references to implicit biases and underlying assumptions

    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
    frey
    -0.89
    meric
    -0.88
    mir
    -0.78
    tis
    -0.75
    cture
    -0.74
    ppa
    -0.73
     Flavoring
    -0.73
    gard
    -0.72
    cellence
    -0.69
     CrossRef
    -0.68
    POSITIVE LOGITS
     consent
    1.03
     acknowledgement
    1.01
     endorsement
    1.00
     acknowledgment
    0.97
     assumption
    0.95
     implicit
    0.89
     assumptions
    0.86
    icit
    0.86
     disav
    0.85
     encouragement
    0.85
    Activations Density 0.048%

    No Known Activations