© 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 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. 3-RES-JB
    11. 24445
    Prev
    Next
    INDEX
    Explanations

    instances where actions involving two or more entities are performed

    oai_token-act-pair · gpt-3.5-turbo

    references to reciprocal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.67
    OV
    -0.66
    haven
    -0.66
    hawks
    -0.64
    stones
    -0.64
    rovers
    -0.63
    Writ
    -0.63
    Bs
    -0.62
     Blaz
    -0.61
    DB
    -0.60
    POSITIVE LOGITS
     successive
    1.18
     individual
    0.85
     iteration
    0.82
     paycheck
    0.81
     subsequent
    0.79
     succeeding
    0.79
     respective
    0.78
    THING
    0.78
    malink
    0.75
     side
    0.74
    Activations Density 0.038%

    No Known Activations