© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18722
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and toxins

    oai_token-act-pair · gpt-3.5-turbo

    chemical compounds and their effects on health

    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
     Camer
    -0.79
     reunion
    -0.78
    ISION
    -0.77
    JJ
    -0.76
    orthy
    -0.71
    views
    -0.71
     Eag
    -0.65
    ariat
    -0.64
    endars
    -0.64
    united
    -0.64
    POSITIVE LOGITS
     chemically
    1.32
     oxid
    1.26
     soluble
    1.26
     metabol
    1.25
     pept
    1.20
     compounds
    1.14
     salts
    1.14
     metabolites
    1.14
     neurot
    1.12
     phosph
    1.11
    Activations Density 0.403%

    No Known Activations