© 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. 2-RES-JB
    11. 2459
    Prev
    Next
    INDEX
    Explanations

    contractions of "should not" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing prohibitions or things that should not be done

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Puzzle
    -0.71
    lip
    -0.69
     Chains
    -0.69
     Liv
    -0.63
    ULT
    -0.62
     Mutant
    -0.61
     Circus
    -0.61
     Showdown
    -0.60
    dress
    -0.58
     Trails
    -0.57
    POSITIVE LOGITS
    't
    1.16
     rightfully
    0.90
    ['
    0.81
    \'
    0.78
     rightly
    0.75
    FontSize
    0.73
     applause
    0.72
    ĪĴ
    0.71
    ered
    0.71
    n
    0.70
    Activations Density 0.005%

    No Known Activations