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. 14886
    Prev
    Next
    INDEX
    Explanations

    phrases related to the significance or importance of events or decisions

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "it" used as a subject or focus 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
    apsed
    -0.73
     Beaver
    -0.65
    UGH
    -0.62
    rete
    -0.61
    Pie
    -0.58
     Jol
    -0.58
     Rampage
    -0.57
    lux
    -0.57
    Major
    -0.57
     BUS
    -0.56
    POSITIVE LOGITS
     allows
    1.44
     prevents
    1.41
     enables
    1.40
     helps
    1.38
     ensures
    1.36
     removes
    1.36
     encourages
    1.35
     eliminates
    1.34
     involves
    1.34
     gives
    1.33
    Activations Density 0.173%

    No Known Activations