© 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. 11-RES-JB
    11. 18645
    Prev
    Next
    INDEX
    Explanations

    mentions of specific levels or concentrations of substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental and health-related measurements or levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cash
    -0.67
    knit
    -0.64
    orial
    -0.62
     revolving
    -0.61
     outsourcing
    -0.60
     manufact
    -0.60
    makers
    -0.60
     awarding
    -0.59
    gro
    -0.59
    stown
    -0.57
    POSITIVE LOGITS
     levels
    1.02
     concentrations
    1.00
     readings
    0.99
     detectable
    0.98
    elsius
    0.93
     measured
    0.90
     Levels
    0.89
     detected
    0.84
    emia
    0.83
     concentration
    0.83
    Activations Density 0.104%

    No Known Activations