© 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. 10-RES-JB
    11. 11235
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is inappropriate or not in the expected or proper condition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating things that are out of proportion or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    rower
    -0.80
    swick
    -0.68
    IDA
    -0.65
    enaries
    -0.65
    erity
    -0.64
    ISA
    -0.64
    ilers
    -0.63
    FORE
    -0.63
    osures
    -0.63
    cause
    -0.62
    POSITIVE LOGITS
    erous
    0.94
     par
    0.81
    whelming
    0.76
    vable
    0.75
     kil
    0.69
     grasp
    0.69
     priorities
    0.68
    humane
    0.67
     fundament
    0.65
    arthy
    0.65
    Activations Density 0.123%

    No Known Activations