© 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. 11-RES-JB
    11. 7570
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features in product descriptions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence structure in technical descriptions

    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
     affili
    -0.82
     recru
    -0.80
     contagious
    -0.79
     contag
    -0.78
     contam
    -0.76
     occupations
    -0.76
     therapist
    -0.75
     foul
    -0.75
     prosec
    -0.74
     volunteering
    -0.74
    POSITIVE LOGITS
    Battery
    1.46
    Hardware
    1.40
    Compared
    1.37
    Samsung
    1.36
    Spec
    1.33
     Compared
    1.31
    Sony
    1.26
    Features
    1.26
    Intel
    1.23
    NVIDIA
    1.22
    Activations Density 0.316%

    No Known Activations