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. 1-RES-JB
    6. 19223
    Prev
    Next
    INDEX
    Explanations

    web platform names and technological jargon

    oai_token-act-pair · gpt-3.5-turbo

    social media engagement and interaction phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chuk
    -0.56
    tnc
    -0.54
    edIn
    -0.52
    Tokens
    -0.51
     indistinguishable
    -0.50
    SpaceEngineers
    -0.50
     theirs
    -0.48
     }}
    -0.47
    onto
    -0.47
    Atlantic
    -0.46
    POSITIVE LOGITS
     largeDownload
    0.65
    ciples
    0.60
    terness
    0.58
    ccording
    0.58
    utions
    0.55
    enhagen
    0.54
     partName
    0.53
    mosp
    0.53
    merce
    0.52
    tesy
    0.52
    Activations Density 6.726%

    No Known Activations