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. 1-RES-JB
    6. 15316
    Prev
    Next
    INDEX
    Explanations

    the word "journey" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ourn" and its variations in various contexts

    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
    FU
    -0.67
     fertile
    -0.63
    Æ
    -0.62
    Population
    -0.62
     thriving
    -0.59
    UG
    -0.59
     breeding
    -0.58
     pid
    -0.58
     self
    -0.57
    IDENT
    -0.56
    POSITIVE LOGITS
    ourn
    1.64
    emouth
    1.28
    swer
    0.95
    rontal
    0.93
    auts
    0.91
    heim
    0.89
    ette
    0.89
    odon
    0.88
    ettes
    0.88
    ilus
    0.87
    Activations Density 0.006%

    No Known Activations