© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 3920
    Prev
    Next
    INDEX
    Explanations

    words related to a specific entity, "Collage"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Collage" or related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    visor
    -0.80
    isSpecialOrderable
    -0.76
    ItemImage
    -0.75
    nor
    -0.73
    thing
    -0.73
    ãĢĮ
    -0.73
    chal
    -0.72
    qua
    -0.71
    scribe
    -0.70
    é¾įåĸļ士
    -0.70
    POSITIVE LOGITS
     Coll
    0.99
    apsed
    0.98
    ateral
    0.93
    apse
    0.88
    Coll
    0.88
    coll
    0.82
    ossus
    0.81
    iseum
    0.79
    ipop
    0.79
    edin
    0.77
    Activations Density 0.002%

    No Known Activations