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. 10-RES-JB
    6. 8601
    Prev
    Next
    INDEX
    Explanations

    verbs related to training or teaching

    oai_token-act-pair · gpt-3.5-turbo

    verbs and actions related to training, assistance, and empowerment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.75
    offer
    -0.66
    wcsstore
    -0.66
     deduction
    -0.65
    route
    -0.63
    vertisement
    -0.62
    cour
    -0.59
     arrangement
    -0.58
     introduction
    -0.58
     favoring
    -0.58
    POSITIVE LOGITS
     them
    1.16
     youngsters
    1.07
     unsuspecting
    1.03
     mankind
    0.96
     young
    0.96
     millions
    0.96
     youths
    0.95
     tens
    0.94
     legions
    0.94
     civilians
    0.93
    Activations Density 0.250%

    No Known Activations