© 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. 1-RES-JB
    11. 8843
    Prev
    Next
    INDEX
    Explanations

    keywords related to medical conditions or treatments

    oai_token-act-pair · gpt-3.5-turbo

    the repeated occurrence of the word "ALL."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.78
    stood
    -0.68
    yip
    -0.67
    hered
    -0.66
     scant
    -0.65
    undai
    -0.65
    lav
    -0.63
    aminer
    -0.62
     minim
    -0.62
     srf
    -0.61
    POSITIVE LOGITS
    OWS
    1.22
    WAYS
    1.11
    ocations
    1.07
    IED
    1.05
    ocating
    1.03
    IES
    1.02
    ALL
    1.01
    ocation
    1.01
    OWER
    1.00
    OW
    1.00
    Activations Density 0.007%

    No Known Activations