© 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. 0-RES-JB
    11. 18117
    Prev
    Next
    INDEX
    Explanations

    references related to technologies or companies with the word "Zoom" in them

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "boom" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nervous
    -0.68
     Nickel
    -0.66
     Sel
    -0.65
     Bentley
    -0.64
     inst
    -0.63
     ``
    -0.63
     nickel
    -0.60
     WD
    -0.59
     disciplinary
    -0.59
     tooth
    -0.59
    POSITIVE LOGITS
    oom
    4.58
    ooming
    1.65
    oo
    1.34
    ombie
    1.18
    ombies
    1.12
    oos
    1.11
    oooooooo
    1.09
     Zoom
    1.07
    oooo
    1.04
    oes
    1.01
    Activations Density 0.017%

    No Known Activations