© 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. 7-RES-JB
    11. 23699
    Prev
    Next
    INDEX
    Explanations

    terms related to athletic training activities

    oai_token-act-pair · gpt-3.5-turbo

    references to training sessions or training camps

    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
    osi
    -0.83
    izontal
    -0.73
    xus
    -0.70
    metics
    -0.66
    bill
    -0.66
    ailable
    -0.66
    ecause
    -0.66
    ACP
    -0.64
     Whedon
    -0.63
    ervatives
    -0.61
    POSITIVE LOGITS
     sessions
    1.00
     camps
    0.97
     camp
    0.97
    camp
    0.94
     regimen
    0.89
     workouts
    0.86
     Peaks
    0.85
     session
    0.81
    inen
    0.79
     wheels
    0.78
    Activations Density 0.033%

    No Known Activations