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. 7716
    Prev
    Next
    INDEX
    Explanations

    phrases related to trying to accomplish something or achieve a goal

    oai_token-act-pair · gpt-3.5-turbo

    the repetitive occurrence of the word "get."

    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
     Archdemon
    -0.65
     depiction
    -0.60
     Wonders
    -0.59
     Duty
    -0.59
     Britann
    -0.58
    iege
    -0.58
    mare
    -0.57
    orney
    -0.56
     Sie
    -0.55
    shock
    -0.54
    POSITIVE LOGITS
     rid
    1.33
    TING
    0.94
     acquainted
    0.86
    away
    0.82
    tin
    0.81
     away
    0.80
    ãĥ³ãĤ¸
    0.77
     distracted
    0.76
     into
    0.75
    aways
    0.75
    Activations Density 0.120%

    No Known Activations