© 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. 23458
    Prev
    Next
    INDEX
    Explanations

    chemicals or substances that are potentially harmful or hazardous to health and the environment

    oai_token-act-pair · gpt-3.5-turbo

    mentions of harmful chemicals and their effects on health and the environment

    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
    ership
    -0.77
    York
    -0.67
    ļé
    -0.66
    oÄŁ
    -0.66
    Commission
    -0.66
     Beaver
    -0.66
    Witness
    -0.65
    esan
    -0.65
     Braves
    -0.64
    Minnesota
    -0.63
    POSITIVE LOGITS
    paces
    1.22
    mith
    1.18
    hips
    1.06
    ervative
    1.01
    ervatives
    1.01
    uits
    1.00
    ynthesis
    1.00
    hops
    0.99
    ensitive
    0.98
    pace
    0.97
    Activations Density 0.240%

    No Known Activations