© 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. 6-RES-JB
    11. 14576
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to different individuals

    oai_token-act-pair · gpt-3.5-turbo

    the structure and presence of the letter 'p' in various contexts

    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
    ledged
    -0.81
    jriwal
    -0.74
    ascus
    -0.69
    arest
    -0.69
     pasture
    -0.66
     clinch
    -0.65
    alore
    -0.65
    lished
    -0.65
    sterdam
    -0.62
    uilt
    -0.62
    POSITIVE LOGITS
    INAL
    0.72
    ãĤ·ãĥ£
    0.67
    kov
    0.65
    ¯¯
    0.64
    Ń·
    0.63
    IAL
    0.62
    berger
    0.60
    èĢħ
    0.60
     Luther
    0.60
     Patton
    0.59
    Activations Density 0.076%

    No Known Activations