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. 7-RES-JB
    6. 22239
    Prev
    Next
    INDEX
    Explanations

    domain-specific technical information or identifiers such as names and codes

    oai_token-act-pair · gpt-3.5-turbo

    references to specific places, entities, and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kab
    -0.67
     Bers
    -0.64
    pic
    -0.62
     BF
    -0.60
    Va
    -0.58
     ko
    -0.57
     gor
    -0.56
     neur
    -0.55
     bio
    -0.54
     chi
    -0.53
    POSITIVE LOGITS
    port
    0.66
    igation
    0.65
    anguages
    0.61
    mingham
    0.59
    porting
    0.58
     âĵĺ
    0.56
    bledon
    0.56
    mber
    0.55
    recated
    0.55
    soDeliveryDate
    0.55
    Activations Density 0.298%

    No Known Activations