© 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
    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. 12277
    Prev
    Next
    INDEX
    Explanations

    phrases or words associated with origins or original sources

    oai_token-act-pair · gpt-3.5-turbo

    terms related to origins or the process of originating

    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
    #$
    -0.74
    SPONSORED
    -0.72
     miscarriage
    -0.62
    FUL
    -0.62
    warming
    -0.61
     creep
    -0.58
     ende
    -0.58
     Jehovah
    -0.58
    zhen
    -0.57
     vigil
    -0.57
    POSITIVE LOGITS
    inated
    2.44
    inating
    2.43
    ination
    2.36
    inate
    2.17
    inates
    2.14
    inations
    2.13
    inators
    2.07
    inator
    2.06
    ined
    1.84
    inatory
    1.78
    Activations Density 0.069%

    No Known Activations