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. 11-RES-JB
    6. 18169
    Prev
    Next
    INDEX
    Explanations

    phrases related to persistence or defiance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to reluctance or avoidance

    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
    igham
    -0.74
    soDeliveryDate
    -0.65
    ighth
    -0.62
     presumably
    -0.59
    ryn
    -0.58
    liam
    -0.58
    KNOWN
    -0.57
    assic
    -0.57
     holiest
    -0.56
    ãĤ¨
    -0.55
    POSITIVE LOGITS
     nor
    1.26
     anymore
    1.23
     either
    1.08
     whatsoever
    0.93
     anytime
    0.89
     slightest
    0.85
     anybody
    0.79
     anyone
    0.75
     anything
    0.73
     any
    0.71
    Activations Density 0.253%

    No Known Activations