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. 8-RES-JB
    6. 23153
    Prev
    Next
    INDEX
    Explanations

    phrases related to pursuing or targeting specific entities or objectives

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "after" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Released
    -0.75
    eller
    -0.74
    aez
    -0.71
    uph
    -0.70
    kept
    -0.68
    bell
    -0.68
    leave
    -0.68
    uten
    -0.66
    hes
    -0.65
    OVER
    -0.65
    POSITIVE LOGITS
     somebody
    0.70
    market
    0.65
    lain
    0.65
     him
    0.62
     whistleblowers
    0.61
     whichever
    0.60
     whoever
    0.59
     someone
    0.59
     something
    0.59
     fossil
    0.59
    Activations Density 0.041%

    No Known Activations