© 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. 10-RES-JB
    11. 2731
    Prev
    Next
    INDEX
    Explanations

    phrases related to natural disasters and their impacts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Flood" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleas
    -0.69
    RAL
    -0.67
     Pupp
    -0.63
     subcontract
    -0.63
    hood
    -0.62
    BIL
    -0.61
     WATCH
    -0.60
    HCR
    -0.58
    cules
    -0.58
     conclud
    -0.58
    POSITIVE LOGITS
    oppy
    1.42
    avour
    1.25
    uffy
    1.25
    inders
    1.24
    oyd
    1.21
    uid
    1.20
    avored
    1.18
    orescent
    1.18
    owers
    1.17
    urry
    1.17
    Activations Density 0.015%

    No Known Activations