© 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. 11-RES-JB
    11. 2541
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrasting opinions or choices

    oai_token-act-pair · gpt-3.5-turbo

    expressions of varying opinions or reactions to a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUn
    -0.65
    ukong
    -0.63
    enna
    -0.63
    ikawa
    -0.62
    uple
    -0.61
    endor
    -0.61
    isin
    -0.61
    abama
    -0.59
    aber
    -0.59
    isu
    -0.59
    POSITIVE LOGITS
     others
    2.31
    Others
    2.17
     Others
    2.17
     some
    1.44
    some
    1.31
    Some
    1.17
     Some
    1.15
     other
    1.10
     SOME
    1.09
    other
    1.06
    Activations Density 0.372%

    No Known Activations