© 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. 2-RES-JB
    11. 9399
    Prev
    Next
    INDEX
    Explanations

    keywords related to harbors

    oai_token-act-pair · gpt-3.5-turbo

    references to harbors and related locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eds
    -0.85
     millenn
    -0.73
    anwhile
    -0.70
    cious
    -0.69
    yson
    -0.68
    Tip
    -0.65
    intendent
    -0.64
    itsch
    -0.64
    gee
    -0.64
    onymous
    -0.63
    POSITIVE LOGITS
     harbor
    1.08
     harbour
    1.00
    bors
    0.89
     harb
    0.85
     cove
    0.85
    lot
    0.74
     Harbour
    0.72
    lash
    0.71
     Cove
    0.70
     Harbor
    0.69
    Activations Density 0.011%

    No Known Activations