© 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. 11753
    Prev
    Next
    INDEX
    Explanations

    sequences related to computer commands or instructions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "âĢ" which likely signifies an encoding issue or placeholder in the text

    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
    çĶ°
    -0.78
    ãĢIJ
    -0.68
     Glou
    -0.61
     sew
    -0.61
     pastry
    -0.61
     polyg
    -0.59
     Syd
    -0.59
     interf
    -0.59
    usterity
    -0.58
    è£ħ
    -0.58
    POSITIVE LOGITS
    Ļ
    1.00
    ¡
    0.99
    ĺ
    0.97
    Ĭ
    0.95
    ľ
    0.95
    ¤
    0.94
    ĸ
    0.93
    Ī
    0.92
    Ń
    0.91
    ķ
    0.90
    Activations Density 0.393%

    No Known Activations