© 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. 2-RES-JB
    11. 9305
    Prev
    Next
    INDEX
    Explanations

    signals related to strong winds

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to strong winds and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.83
    Tok
    -0.67
    atern
    -0.66
    arth
    -0.65
    onyms
    -0.62
    arenthood
    -0.61
     entitlement
    -0.59
    endants
    -0.59
    Mur
    -0.59
    ĨĴ
    -0.59
    POSITIVE LOGITS
     winds
    1.21
    storms
    1.03
     Winds
    1.00
     gust
    0.93
     currents
    0.88
     wind
    0.83
     blowing
    0.83
    Wind
    0.82
     chill
    0.81
     breeze
    0.79
    Activations Density 0.011%

    No Known Activations