© 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. 4-RES-JB
    11. 6316
    Prev
    Next
    INDEX
    Explanations

    objects or materials made of cotton

    oai_token-act-pair · gpt-3.5-turbo

    references to cotton

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

    No Comments

    Negative Logits
    aphael
    -0.81
    ablishment
    -0.74
    sets
    -0.72
    */(
    -0.72
    ĺħ
    -0.72
     behav
    -0.71
    onym
    -0.71
    onyms
    -0.69
    CVE
    -0.68
    ctica
    -0.68
    POSITIVE LOGITS
    seed
    1.12
     cotton
    1.01
     wool
    0.98
     candy
    0.96
    mouth
    0.92
    wood
    0.92
    bean
    0.92
     yarn
    0.92
     gin
    0.91
    grass
    0.91
    Activations Density 0.010%

    No Known Activations