© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 9916
    Prev
    Next
    INDEX
    Explanations

    variations or differences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of difference or distinction

    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
    advertising
    -0.67
    Optional
    -0.57
     Sponsor
    -0.57
    OIL
    -0.54
    Bern
    -0.54
     Beans
    -0.53
    adobe
    -0.53
    vp
    -0.53
     Nile
    -0.52
     Saud
    -0.52
    POSITIVE LOGITS
    iating
    1.67
    iates
    1.60
    iator
    1.40
    iated
    1.32
     than
    1.31
    ials
    1.19
    iate
    1.14
    iable
    1.14
    iations
    1.09
    iation
    1.02
    Activations Density 0.061%

    No Known Activations