© 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. 7-RES-JB
    11. 13358
    Prev
    Next
    INDEX
    Explanations

    mentions of academics or scholars

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scholars and academic research

    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
     Labrador
    -0.74
     Ventura
    -0.72
     Krypt
    -0.67
     territ
    -0.66
     Bots
    -0.59
     Racing
    -0.59
     abrupt
    -0.57
     Incredible
    -0.56
     chaotic
    -0.56
     manslaughter
    -0.56
    POSITIVE LOGITS
    sonian
    1.32
     scholar
    1.04
    hip
    1.03
     scholars
    1.01
    olars
    0.96
     Scholars
    0.92
    craft
    0.90
    hips
    0.87
     laureate
    0.85
    itatively
    0.84
    Activations Density 0.043%

    No Known Activations