© 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. 10900
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or initiatives being undertaken

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the word "By" followed by actions or proposals involving analyses, connections, or recommendations

    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
    atem
    -0.76
    SPONSORED
    -0.75
    hyde
    -0.67
    abs
    -0.65
    isable
    -0.63
    blast
    -0.62
    ernal
    -0.61
    ptive
    -0.60
    >)
    -0.60
    icket
    -0.60
    POSITIVE LOGITS
     contrast
    1.14
     virtue
    1.07
    akuya
    0.98
     implication
    0.92
    catch
    0.86
    stand
    0.78
     default
    0.77
     definition
    0.76
     extension
    0.76
     sheer
    0.74
    Activations Density 0.042%

    No Known Activations