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. 12-RES-JB
    6. 14656
    Prev
    Next
    INDEX
    Explanations

    phrases related to promoting or supporting journalism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to journalism or discussions about its value and relevance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hess
    -0.62
    minster
    -0.59
     liner
    -0.58
    notation
    -0.58
     baseman
    -0.57
    eric
    -0.57
     Marion
    -0.56
    cker
    -0.56
    INGTON
    -0.54
     Barney
    -0.54
    POSITIVE LOGITS
    gdala
    0.87
     excellence
    0.72
     Standards
    0.72
    mbuds
    0.71
     Integrity
    0.70
    tek
    0.66
    rored
    0.65
    orial
    0.64
    BIL
    0.63
     License
    0.62
    Activations Density 0.020%

    No Known Activations