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. 11-RES-JB
    6. 8564
    Prev
    Next
    INDEX
    Explanations

    company names and related entities

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebin
    -0.81
    flush
    -0.76
    sed
    -0.76
     seeming
    -0.73
     worse
    -0.73
     anyway
    -0.72
     messing
    -0.72
    gging
    -0.70
     tho
    -0.68
     flick
    -0.68
    POSITIVE LOGITS
     strives
    1.73
     welcomes
    1.62
     recognizes
    1.38
     participates
    1.37
     seeks
    1.36
     intends
    1.34
     conducts
    1.34
     invites
    1.32
     utilizes
    1.31
     encourages
    1.30
    Activations Density 0.381%

    No Known Activations