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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18920
    Prev
    Next
    INDEX
    Explanations

    instances of the word "free"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of free offers or services

    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
    older
    -0.79
    igham
    -0.75
     sidx
    -0.72
    onductor
    -0.71
    need
    -0.68
     Takeru
    -0.66
    ents
    -0.65
    itect
    -0.65
    ioned
    -0.64
    onduct
    -0.64
    POSITIVE LOGITS
    bies
    1.55
    bie
    1.33
    zers
    1.24
     roam
    1.01
    zing
    0.99
     downloadable
    0.97
     eBook
    0.95
    zes
    0.92
    zer
    0.91
     download
    0.87
    Activations Density 0.036%

    No Known Activations