Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22834
    Prev
    Next
    INDEX
    Explanations

    words related to quotations and direct speech

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and their patterns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.81
     Kem
    -0.81
     mech
    -0.79
     mosquit
    -0.78
     Å
    -0.77
    igr
    -0.77
     kettle
    -0.75
     wedge
    -0.75
     cam
    -0.74
     Thunderbolt
    -0.73
    POSITIVE LOGITS
    Rich
    2.41
     Richards
    2.08
     Richardson
    2.05
     Rich
    2.02
     Richie
    1.69
    rich
    1.54
     Richmond
    1.19
     rich
    1.14
     Ric
    1.08
     Nichols
    1.07
    Activations Density 0.190%

    No Known Activations