© 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. 8-RES-JB
    11. 20435
    Prev
    Next
    INDEX
    Explanations

    quotations within statements

    oai_token-act-pair · gpt-3.5-turbo

    quoted speech or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slam
    -0.85
     dunk
    -0.83
     roar
    -0.83
     mud
    -0.82
     shit
    -0.81
     pee
    -0.80
     jug
    -0.80
     crap
    -0.80
     tunnel
    -0.79
     landslide
    -0.78
    POSITIVE LOGITS
    Therefore
    1.38
    Thus
    1.34
    Additionally
    1.32
    Moreover
    1.31
    Our
    1.27
    This
    1.27
    Furthermore
    1.27
    Based
    1.26
    While
    1.26
    Although
    1.25
    Activations Density 0.180%

    No Known Activations