© 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. 9-RES-JB
    11. 7171
    Prev
    Next
    INDEX
    Explanations

    phrases related to news interviews or public statements

    oai_token-act-pair · gpt-3.5-turbo

    references to interviews or formal discussions

    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
    }}}
    -0.60
    ''.
    -0.57
    pes
    -0.54
     Ples
    -0.54
     Written
    -0.53
    $.
    -0.53
    wd
    -0.53
    malink
    -0.53
    udic
    -0.52
    default
    -0.52
    POSITIVE LOGITS
    that
    1.02
     that
    0.92
    è¦ļéĨĴ
    0.76
    :"
    0.66
     whether
    0.65
     why
    0.64
    ouncing
    0.64
     "[
    0.63
    ãĤ¤ãĥĪ
    0.63
     how
    0.63
    Activations Density 0.320%

    No Known Activations