© 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. 14582
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "consists"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe components or parts of a whole

    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
    iaries
    -0.66
    inition
    -0.63
    AIDS
    -0.63
    soType
    -0.63
     confir
    -0.62
     justifies
    -0.62
     challeng
    -0.60
    orah
    -0.60
    dad
    -0.59
     Advocate
    -0.58
    POSITIVE LOGITS
     varying
    0.84
     sorts
    0.82
    umbn
    0.78
     several
    0.74
     dots
    0.73
     either
    0.72
     three
    0.71
     alternating
    0.69
     pure
    0.68
     five
    0.68
    Activations Density 0.075%

    No Known Activations