© 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. 8-RES-JB
    11. 6220
    Prev
    Next
    INDEX
    Explanations

    words related to destabilization and jeopardization

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with destabilization and jeopardy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blindly
    -0.70
    tower
    -0.67
     Faw
    -0.61
    perty
    -0.61
     PU
    -0.60
    avorite
    -0.58
     Crawford
    -0.58
    BU
    -0.58
     Ao
    -0.57
     Clerk
    -0.56
    POSITIVE LOGITS
    izing
    2.47
    ization
    2.42
    ized
    2.41
    izations
    2.13
    izes
    2.12
    isation
    2.12
    izers
    2.08
    ising
    2.08
    ised
    2.06
    ize
    2.03
    Activations Density 0.137%

    No Known Activations