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. 4-RES-JB
    6. 3848
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific people or places

    oai_token-act-pair · gpt-3.5-turbo

    specific references to political, social, or cultural issues and events

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

    No Comments

    Negative Logits
     saline
    -0.50
    sed
    -0.42
     oneself
    -0.42
    åĬ
    -0.41
    itious
    -0.41
    )=
    -0.41
    reek
    -0.40
     Hoo
    -0.40
    gro
    -0.40
    ulative
    -0.40
    POSITIVE LOGITS
    abilia
    0.58
    ungle
    0.46
     empire
    0.45
     fame
    0.45
    hops
    0.44
    edom
    0.43
     Belfast
    0.43
    being
    0.42
    chool
    0.41
    uckles
    0.40
    Activations Density 1.459%

    No Known Activations