© 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. 12615
    Prev
    Next
    INDEX
    Explanations

    words related to academic writing and analysis

    oai_token-act-pair · gpt-3.5-turbo

    expressions of analysis or evaluation involving proposals and contributions

    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
     Canaveral
    -0.74
    lbs
    -0.65
     snapped
    -0.64
    Owner
    -0.64
    adelphia
    -0.63
     Dubai
    -0.63
     Carnage
    -0.61
    vernight
    -0.60
     UAE
    -0.60
    venge
    -0.59
    POSITIVE LOGITS
     epist
    1.15
     methodological
    1.12
     hypotheses
    1.11
     philosophers
    1.09
     empirical
    1.08
     empir
    1.07
     eluc
    1.06
     explanatory
    1.04
     quotations
    1.03
     fallacy
    1.02
    Activations Density 1.579%

    No Known Activations