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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18039
    Prev
    Next
    INDEX
    Explanations

    phrases related to optimal or superior conditions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to optimal conditions and the concept of "best" in various contexts

    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
     earthqu
    -0.73
     unfocusedRange
    -0.69
     guiActiveUn
    -0.62
     exting
    -0.61
    ç«
    -0.60
    otom
    -0.60
     teasp
    -0.60
    erey
    -0.59
    ruciating
    -0.58
    eeper
    -0.58
    POSITIVE LOGITS
     imaginable
    2.15
     possible
    1.81
     EVER
    1.66
     ever
    1.51
     conceivable
    1.45
     practicable
    1.38
     Possible
    1.33
    ever
    1.31
     feasible
    1.17
     available
    1.15
    Activations Density 0.246%

    No Known Activations