© 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
    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. 20582
    Prev
    Next
    INDEX
    Explanations

    direct or reported speech where a message or statement is being communicated

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and its frequency in different contexts

    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
    thood
    -0.83
    pai
    -0.78
    ãĥĺãĥ©
    -0.72
    aceae
    -0.70
    iances
    -0.70
    obyl
    -0.69
    /**
    -0.68
    omics
    -0.67
    uria
    -0.67
    \\\\\\\\
    -0.66
    POSITIVE LOGITS
     Huffington
    1.33
     BBC
    1.29
     Associated
    1.29
     Guardian
    1.27
     Daily
    1.24
     Observer
    1.17
     Evening
    1.11
     Examiner
    1.10
     Chronicle
    1.09
     newspaper
    1.09
    Activations Density 0.076%

    No Known Activations