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. 636
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions, particularly actions involving communication or change

    oai_token-act-pair · gpt-3.5-turbo

    actions and responsibilities related to societal issues

    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
    rawdownloadcloneembedreportprint
    -0.67
     Nau
    -0.62
     Gh
    -0.61
     Bucs
    -0.58
     Tue
    -0.58
     fracturing
    -0.57
     Paste
    -0.55
    ItemTracker
    -0.55
     Nep
    -0.54
     Hof
    -0.53
    POSITIVE LOGITS
     oneself
    1.21
     RELEASE
    0.93
    ardless
    0.71
     yourself
    0.70
    igl
    0.69
     alternate
    0.66
    itate
    0.66
    èĢħ
    0.64
    enance
    0.64
     ourselves
    0.63
    Activations Density 0.288%

    No Known Activations