© 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. 12650
    Prev
    Next
    INDEX
    Explanations

    text and characters that may indicate programming code, particularly associated with digital and virtual reality-related terms

    oai_token-act-pair · gpt-3.5-turbo

    words associated with digital technology and virtual reality

    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
     respectively
    -0.59
    ]."
    -0.53
    .</
    -0.53
    $.
    -0.51
    )."
    -0.49
    }.
    -0.48
     thereby
    -0.47
     thereto
    -0.46
    .).
    -0.46
     etc
    -0.44
    POSITIVE LOGITS
    ':
    0.43
    vez
    0.43
    \":
    0.40
     partName
    0.40
    reenshots
    0.40
    yna
    0.37
     Variant
    0.37
    abases
    0.37
    ibliography
    0.37
    cloneembedreportprint
    0.36
    Activations Density 3.042%

    No Known Activations