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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 8214
    Prev
    Next
    INDEX
    Explanations

    words related to skincare and medical treatments

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forth
    -0.79
     QC
    -0.63
     Boko
    -0.62
     ç¥ŀ
    -0.61
    matched
    -0.61
     Origin
    -0.61
     Oo
    -0.59
    cross
    -0.59
    makers
    -0.58
     Decker
    -0.58
    POSITIVE LOGITS
    acies
    1.26
    atory
    1.14
    acist
    1.12
    acles
    1.12
    pir
    1.09
    acular
    1.05
    ators
    1.04
    ysc
    1.02
    acet
    1.00
    atus
    0.99
    Activations Density 0.010%

    No Known Activations