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

    Neuronpedia

    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. 9-RES-JB
    11. 22907
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    the word "preexisting."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pru
    -0.76
    getic
    -0.69
     Rough
    -0.69
    à¨
    -0.68
     NETWORK
    -0.66
    à©
    -0.65
     behavi
    -0.65
    å§
    -0.64
    DERR
    -0.63
    NRS
    -0.62
    POSITIVE LOGITS
    aminer
    1.32
    pert
    1.15
    peria
    1.12
    posed
    1.12
    posure
    1.10
    avier
    1.08
    imity
    1.07
    ternal
    1.06
    actly
    1.04
    odus
    1.03
    Activations Density 0.053%

    No Known Activations