© 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. 7-RES-JB
    11. 14417
    Prev
    Next
    INDEX
    Explanations

    words related to the term "serial", especially in the context of identification numbers or criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to serial numbers and serial-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aneers
    -0.80
    luck
    -0.80
    wich
    -0.74
    chens
    -0.74
    llan
    -0.74
    uden
    -0.72
    arest
    -0.71
    atche
    -0.71
    reath
    -0.70
     Syri
    -0.68
    POSITIVE LOGITS
    ized
    1.19
    ization
    1.04
    isation
    1.03
    izable
    1.01
    ised
    1.01
    izations
    0.98
     killers
    0.98
     killer
    0.93
     monog
    0.89
    izing
    0.88
    Activations Density 0.034%

    No Known Activations