© 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. 6-RES-JB
    11. 5138
    Prev
    Next
    INDEX
    Explanations

    mentions of the abbreviation "BI"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "BIRMINGHAM" along with associated numerical or ranking information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.86
    isting
    -0.78
    ional
    -0.71
    bilt
    -0.70
    izational
    -0.68
    izers
    -0.66
    ength
    -0.64
    nery
    -0.64
    earchers
    -0.64
    entially
    -0.64
    POSITIVE LOGITS
    ĨĴ
    0.91
    Īè
    0.91
    ļéĨĴ
    0.89
    ī
    0.89
    undo
    0.88
    ases
    0.88
    ased
    0.83
    ĸļ
    0.81
    omedical
    0.79
    asing
    0.78
    Activations Density 0.027%

    No Known Activations