© 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 EvalsExportsAPI 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. 7-RES-JB
    11. 1770
    Prev
    Next
    INDEX
    Explanations

    mentions of the abbreviation "MI" with associated alphanumeric values

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "MI" and related identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holders
    -0.76
    sworth
    -0.76
    holder
    -0.75
    \\\\\\\\
    -0.75
    language
    -0.74
    shell
    -0.73
    size
    -0.73
    ding
    -0.70
    modules
    -0.70
    mans
    -0.70
    POSITIVE LOGITS
    AMI
    1.13
    PS
    0.99
    HAEL
    0.97
    KE
    0.90
    eredith
    0.82
    uppet
    0.81
    XT
    0.81
    ovember
    0.80
    LE
    0.72
    xtap
    0.72
    Activations Density 0.018%

    No Known Activations