Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20338
    Prev
    Next
    INDEX
    Explanations

    phrases related to security breaches or intrusions

    oai_token-act-pair · gpt-3.5-turbo

    references to internal and external structures or conditions, particularly in a technological or biological context

    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
    SHIP
    -0.85
    creen
    -0.82
    hare
    -0.78
    fully
    -0.75
    fulness
    -0.72
     gradual
    -0.70
    LESS
    -0.69
     paved
    -0.68
     fever
    -0.65
     spinning
    -0.64
    POSITIVE LOGITS
    uders
    1.79
    uding
    1.65
    usions
    1.49
    uded
    1.46
    udes
    1.38
    usion
    1.31
    uder
    1.30
    aband
    1.29
    usive
    1.29
    ude
    1.17
    Activations Density 0.040%

    No Known Activations