© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 7300
    Prev
    Next
    INDEX
    Explanations

    contractions of "could not" used in sentences

    oai_token-act-pair · gpt-3.5-turbo

    negations and expressions of inability or impossibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Charity
    -0.59
    ature
    -0.58
     Signed
    -0.58
    mine
    -0.57
    ahime
    -0.56
    iable
    -0.55
     Identification
    -0.55
    imity
    -0.54
     Actions
    -0.52
     Cutter
    -0.52
    POSITIVE LOGITS
     possibly
    0.83
     muster
    0.81
     afford
    0.79
     conce
    0.79
    liga
    0.78
     foresee
    0.77
     conceive
    0.74
    cffffcc
    0.72
     withstand
    0.70
    ħĭ
    0.69
    Activations Density 0.119%

    No Known Activations