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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20629
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical analysis and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to statistical error and data interpretation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usalem
    -0.66
     Tomorrow
    -0.66
    akeru
    -0.60
     Classics
    -0.59
    ovies
    -0.59
     Lands
    -0.59
     loved
    -0.58
     Normandy
    -0.56
     Ready
    -0.56
     Toro
    -0.56
    POSITIVE LOGITS
     causation
    0.77
    cific
    0.71
     jurisd
    0.71
     qualitative
    0.71
    ).[
    0.70
    )).
    0.70
    .).
    0.69
     quant
    0.68
     empir
    0.68
    soType
    0.68
    Activations Density 1.199%

    No Known Activations