© 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. 11-RES-JB
    11. 9398
    Prev
    Next
    INDEX
    Explanations

    phrases related to advice and precautions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal situations and responsibilities

    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
    ECD
    -0.63
    ancies
    -0.62
    agara
    -0.61
     princip
    -0.59
    untled
    -0.58
    orthy
    -0.57
    ashtra
    -0.55
    agements
    -0.54
    dozen
    -0.54
    vard
    -0.53
    POSITIVE LOGITS
     it
    1.35
    it
    1.35
     It
    1.16
    It
    1.13
    its
    1.11
    Its
    1.10
     Its
    1.01
    inventoryQuantity
    1.00
     IT
    0.93
     its
    0.90
    Activations Density 0.254%

    No Known Activations