© 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. 16658
    Prev
    Next
    INDEX
    Explanations

    examples of situations where a statement or action is done in spite of potential drawbacks or challenges

    oai_token-act-pair · gpt-3.5-turbo

    the word "even" in contexts suggesting contrast or contradiction

    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
    aim
    -0.74
    uble
    -0.68
    ENTION
    -0.67
    rend
    -0.66
    mber
    -0.65
    emp
    -0.64
    NULL
    -0.64
    asus
    -0.64
    士
    -0.62
    =-=-=-=-=-=-=-=-
    -0.61
    POSITIVE LOGITS
     though
    1.59
     if
    1.26
     tho
    1.19
    handedly
    0.99
     when
    0.96
    though
    0.90
     after
    0.88
     assuming
    0.86
     amidst
    0.84
     remotely
    0.83
    Activations Density 0.049%

    No Known Activations