Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 5869
    Prev
    Next
    INDEX
    Explanations

    mentions of influential or significant individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imo
    -0.73
    weed
    -0.65
    MAC
    -0.62
    bone
    -0.60
    inducing
    -0.58
    era
    -0.57
    odor
    -0.57
    bike
    -0.55
    âĺħ
    -0.55
    quote
    -0.55
    POSITIVE LOGITS
     been
    0.97
    oday
    0.90
     gotta
    0.88
     seen
    0.82
     ourselves
    0.78
     gotten
    0.78
     Been
    0.74
    ĸļ
    0.73
     begun
    0.73
    ortium
    0.72
    Activations Density 0.129%

    No Known Activations