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. 15192
    Prev
    Next
    INDEX
    Explanations

    locations and descriptive details within a narrative

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

    specific geographical locations and landmarks

    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
    phas
    -0.76
    ially
    -0.67
     advisers
    -0.63
     sidel
    -0.58
     repetition
    -0.58
     benign
    -0.57
     quotas
    -0.57
     acknowled
    -0.56
    inarily
    -0.56
    respond
    -0.55
    POSITIVE LOGITS
    !!!!
    1.08
    !!!
    1.01
     ðŁĺ
    1.01
     !!
    1.01
    !!
    1.00
    ?!
    0.95
     Airport
    0.95
     :)
    0.94
    !!!!!
    0.94
    !!!!!!!!
    0.93
    Activations Density 0.383%

    No Known Activations