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. 4-RES-JB
    6. 23436
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences introducing additional information or considerations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Besides" indicating additional information or points being made

    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
    eway
    -0.74
    abolic
    -0.72
    avis
    -0.71
    acy
    -0.69
     charism
    -0.67
    ANS
    -0.64
    adr
    -0.61
    edy
    -0.60
    itory
    -0.60
    iste
    -0.59
    POSITIVE LOGITS
     knowing
    0.72
    ãĥĦ
    0.71
     enjoying
    0.71
     ours
    0.71
    lihood
    0.68
    ional
    0.67
     contributing
    0.63
    being
    0.63
     supplying
    0.63
     serving
    0.62
    Activations Density 0.012%

    No Known Activations