© 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. 10-RES-JB
    11. 4687
    Prev
    Next
    INDEX
    Explanations

    names or phrases related to specific individuals, possibly in relation to a plot involving deception or schemes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    picking
    -0.69
    driving
    -0.66
    laugh
    -0.66
    sworth
    -0.66
    rified
    -0.61
    luck
    -0.61
    short
    -0.61
    slow
    -0.61
    packed
    -0.60
    stable
    -0.59
    POSITIVE LOGITS
    ñ
    1.30
    ÅŁ
    1.20
    ño
    1.19
    ç
    1.16
    ña
    1.08
    ÄŁ
    1.02
    ð
    1.02
    ÅĤ
    0.99
    ÃŁ
    0.98
    ppa
    0.95
    Activations Density 0.092%

    No Known Activations