© 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. 10-RES-JB
    11. 20517
    Prev
    Next
    INDEX
    Explanations

    significant statements or quotations

    oai_token-act-pair · gpt-3.5-turbo

    statements or descriptions related to performance or conduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "âĢ¦
    -1.47
     "âĢ¦
    -1.32
    âĢ¦"
    -1.25
    âĢ¦
    -1.21
     –
    -1.17
    –
    -1.08
    âĢ³
    -1.07
    âĢ¦)
    -1.06
     ðŁĻĤ
    -1.02
    âĢ¦]
    -0.86
    POSITIVE LOGITS
    �
    2.51
     ''
    2.43
     �
    2.41
    .''
    2.39
    ''
    2.29
     ``
    2.18
    ``
    2.17
    ,''
    2.16
    .�
    2.15
    ''.
    2.07
    Activations Density 0.070%

    No Known Activations