© 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. 7-RES-JB
    11. 4077
    Prev
    Next
    INDEX
    Explanations

    chemicals that are harmful or toxic to health

    oai_token-act-pair · gpt-3.5-turbo

    terms related to harmful agricultural chemicals and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Books
    -0.85
    ento
    -0.78
    orld
    -0.78
    ÅĤ
    -0.74
    TeX
    -0.74
    DEM
    -0.72
    ership
    -0.72
    kus
    -0.71
    Fal
    -0.69
    apest
    -0.68
    POSITIVE LOGITS
     residue
    1.01
    icity
    0.96
     soluble
    0.95
     additives
    0.94
     residues
    0.94
     additive
    0.94
     glutamate
    0.90
     compounds
    0.89
     ions
    0.89
     oxid
    0.88
    Activations Density 0.138%

    No Known Activations