© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 5885
    Prev
    Next
    INDEX
    Explanations

    references to economic policies or achievements

    oai_token-act-pair · gpt-3.5-turbo

    actions related to personal or social engagements, particularly those that involve participation and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AND
    -0.58
    ?,
    -0.57
     and
    -0.56
    ibrary
    -0.53
    yip
    -0.51
     And
    -0.51
     ],
    -0.51
    >,
    -0.50
    And
    -0.49
     -->
    -0.48
    POSITIVE LOGITS
     accordingly
    1.13
     thereafter
    0.93
     thereof
    0.86
     therein
    0.80
     alike
    0.76
     thereto
    0.75
     consequently
    0.75
     attRot
    0.69
     afterward
    0.69
     importantly
    0.62
    Activations Density 2.547%

    No Known Activations