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. 0-RES-JB
    6. 24197
    Prev
    Next
    INDEX
    Explanations

    words related to substances, particularly adrenaline

    oai_token-act-pair · gpt-3.5-turbo

    references to the drug "analgin" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fit
    -0.85
     buck
    -0.77
    Zip
    -0.75
     Hatch
    -0.72
     Goff
    -0.67
     AFL
    -0.66
     harb
    -0.65
    Rail
    -0.65
     bos
    -0.65
    lee
    -0.65
    POSITIVE LOGITS
    alin
    2.14
     regain
    1.66
    aline
    1.63
    ANA
    1.53
     Lenovo
    1.13
    uria
    1.13
    udo
    1.12
     retrieve
    1.11
     retrieved
    1.09
     Trident
    1.06
    Activations Density 0.056%

    No Known Activations