© 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. 10446
    Prev
    Next
    INDEX
    Explanations

    locations or positional information

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or points of origin

    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
    quel
    -0.76
    ATURE
    -0.70
    lator
    -0.68
    efe
    -0.63
    astical
    -0.63
    endiary
    -0.63
    enegger
    -0.63
    emon
    -0.63
    emed
    -0.61
    esis
    -0.61
    POSITIVE LOGITS
    abouts
    1.25
    upon
    1.15
     else
    1.07
     exactly
    1.02
    soever
    0.89
     they
    0.89
    ver
    0.81
    fore
    0.76
     things
    0.74
     we
    0.73
    Activations Density 0.040%

    No Known Activations