© 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. 16708
    Prev
    Next
    INDEX
    Explanations

    instances of the word "support" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of support

    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
    chin
    -0.72
    tein
    -0.71
    sung
    -0.69
    kered
    -0.65
    corn
    -0.65
    ellen
    -0.60
    ucket
    -0.60
    apeake
    -0.59
    wed
    -0.58
    ãĥ¥
    -0.58
    POSITIVE LOGITS
    ive
    0.96
     mechanisms
    0.88
    heses
    0.86
     services
    0.83
     networks
    0.82
     Vector
    0.80
    iveness
    0.79
    ively
    0.75
     beams
    0.73
    ament
    0.73
    Activations Density 0.061%

    No Known Activations