© 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. 20184
    Prev
    Next
    INDEX
    Explanations

    distinguishing and differentiating between objects or concepts based on specific criteria

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of differentiation or distinction

    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
     Omni
    -0.70
    ttp
    -0.67
    odd
    -0.63
     Epidem
    -0.61
    Ö¼
    -0.59
     credits
    -0.58
    onz
    -0.58
     roller
    -0.58
    OD
    -0.57
     Rao
    -0.57
    POSITIVE LOGITS
     distinguish
    1.06
    ĸļ
    1.03
     distinguishing
    0.95
     differentiate
    0.93
     distingu
    0.93
    inctions
    0.92
     distinguishes
    0.92
    ĨĴ
    0.92
    ively
    0.89
     warr
    0.89
    Activations Density 0.008%

    No Known Activations