© 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. 3-RES-JB
    11. 10797
    Prev
    Next
    INDEX
    Explanations

    topics, events, or situations that are considered extreme or out of the ordinary

    oai_token-act-pair · gpt-3.5-turbo

    references to extreme situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yard
    -0.84
    nance
    -0.81
    sburgh
    -0.80
    fman
    -0.79
    shaw
    -0.79
    bats
    -0.79
    ËĪ
    -0.78
    omo
    -0.77
    stown
    -0.76
    nexus
    -0.73
    POSITIVE LOGITS
     extreme
    0.90
     extremes
    0.89
     lengths
    0.86
     temperatures
    0.80
     amounts
    0.77
     measures
    0.75
     poverty
    0.75
    Extreme
    0.75
     vetting
    0.74
     ideologies
    0.73
    Activations Density 0.011%

    No Known Activations