Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17446
    Prev
    Next
    INDEX
    Explanations

    words related to student-athletes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to athletic participation and student-athletes

    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
     shorth
    -0.71
     Reloaded
    -0.70
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
     Wizard
    -0.64
     sterling
    -0.62
     Gemini
    -0.61
    ITED
    -0.61
     Mog
    -0.60
    enhagen
    -0.60
     Sahara
    -0.60
    POSITIVE LOGITS
    aniel
    1.18
    lete
    1.15
    urst
    1.14
    ouse
    1.09
    ulhu
    1.04
    reshold
    1.02
    ouses
    1.02
    letes
    0.96
    olics
    0.94
    opter
    0.94
    Activations Density 0.036%

    No Known Activations