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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 14396
    Prev
    Next
    INDEX
    Explanations

    items or objects in specific locations or positions within a setting

    oai_token-act-pair · gpt-3.5-turbo

    specific locations and physical objects within a scene

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uel
    -0.66
    emort
    -0.65
    emouth
    -0.63
    aiden
    -0.62
    effective
    -0.61
    since
    -0.60
    requisites
    -0.60
    ennial
    -0.59
    enna
    -0.59
    $.
    -0.58
    POSITIVE LOGITS
     lies
    1.34
     resides
    1.26
     sits
    1.24
     lur
    1.21
     hangs
    1.18
     rests
    1.03
     stands
    0.97
     emerges
    0.97
     comes
    0.96
     lays
    0.96
    Activations Density 0.182%

    No Known Activations