© 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. 1-RES-JB
    11. 16829
    Prev
    Next
    INDEX
    Explanations

    terms related to the process of distilling

    oai_token-act-pair · gpt-3.5-turbo

    words related to distillation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tes
    -0.91
    swick
    -0.70
    deen
    -0.70
    eker
    -0.69
    ENA
    -0.68
    ton
    -0.68
    PsyNetMessage
    -0.67
     Daw
    -0.67
    glers
    -0.65
    DF
    -0.65
    POSITIVE LOGITS
     dist
    1.25
    ribut
    1.19
    illery
    1.09
    anced
    0.99
    ributes
    0.93
    aste
    0.89
    illation
    0.87
    ortion
    0.86
    Dist
    0.86
    enfranch
    0.84
    Activations Density 0.006%

    No Known Activations