© 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. 11114
    Prev
    Next
    INDEX
    Explanations

    phrases where a comparison is made between two alternatives, emphasizing a preference for one over the other

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating preference or alternatives

    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
    lance
    -0.72
    cia
    -0.72
    LO
    -0.71
    CCC
    -0.70
    meric
    -0.70
    iren
    -0.70
    ulner
    -0.69
    estern
    -0.69
    DO
    -0.69
    WIND
    -0.68
    POSITIVE LOGITS
     relying
    1.47
     letting
    1.16
     bothering
    1.12
     merely
    1.12
     simply
    1.11
     necessarily
    1.10
     focusing
    1.10
     risking
    1.09
     concentrating
    1.08
     having
    1.05
    Activations Density 0.065%

    No Known Activations