© 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. 7-RES-JB
    11. 2151
    Prev
    Next
    INDEX
    Explanations

    mentions of an entity called "Coll" followed by a numeric value (e.g. Coll 9, Coll 8)

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Coll" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oshenko
    -0.78
    thing
    -0.72
    ¥µ
    -0.71
    visor
    -0.71
    qua
    -0.66
    fulness
    -0.66
    DragonMagazine
    -0.66
    isSpecialOrderable
    -0.65
    PDATE
    -0.64
    BLE
    -0.63
    POSITIVE LOGITS
    ateral
    1.22
    apse
    1.04
    oqu
    1.02
    iery
    1.02
    ocation
    1.02
    ision
    1.02
    iseum
    1.00
    ossus
    1.00
    apsed
    1.00
    ider
    0.98
    Activations Density 0.027%

    No Known Activations