© 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. 6-RES-JB
    11. 10668
    Prev
    Next
    INDEX
    Explanations

    actions related to cancellation or removal

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the cancellation or removal of events, documents, or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idth
    -0.82
    rouse
    -0.69
    ivities
    -0.65
     displeasure
    -0.64
    MAT
    -0.62
    actual
    -0.62
    rics
    -0.61
    PRES
    -0.59
    assadors
    -0.59
    Fit
    -0.59
    POSITIVE LOGITS
     entirely
    0.82
     altogether
    0.79
     by
    0.76
     aback
    0.76
     abruptly
    0.72
     miser
    0.72
     unanimously
    0.68
     completely
    0.68
     laughing
    0.66
    sole
    0.65
    Activations Density 0.202%

    No Known Activations