© 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. 8-RES-JB
    11. 24306
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases or clauses introduced by words such as 'which', 'that', and 'and'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce or refer to conditions and explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiName
    -0.71
     ();
    -0.64
    .............
    -0.63
     :=
    -0.63
    ":[{"
    -0.62
    HOU
    -0.61
    foreseen
    -0.60
    ................................
    -0.59
     âĢº
    -0.58
     ."
    -0.57
    POSITIVE LOGITS
    ?)
    1.55
    !)
    1.52
    -)
    1.41
    )
    1.40
    )."
    1.39
    !),
    1.38
    ?),
    1.38
    ),"
    1.37
    *)
    1.32
    ?).
    1.31
    Activations Density 0.278%

    No Known Activations