© 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. 8-RES-JB
    11. 20252
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration

    oai_token-act-pair · gpt-3.5-turbo

    the word "Coll" in various contexts, typically related to collaborative, collective, or collision themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oshenko
    -0.74
    fulness
    -0.74
    chal
    -0.73
    thing
    -0.71
    visor
    -0.66
    BLE
    -0.66
    ¥µ
    -0.65
    geons
    -0.63
    culosis
    -0.63
    qua
    -0.62
    POSITIVE LOGITS
    ateral
    1.14
    oqu
    1.06
    apsed
    1.06
    apse
    1.04
    ocation
    1.03
    ision
    1.00
    ossus
    1.00
    iery
    0.98
    iseum
    0.98
    ider
    0.96
    Activations Density 0.028%

    No Known Activations