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. 0-RES-JB
    6. 19408
    Prev
    Next
    INDEX
    Explanations

    words related to complaints or complaints themselves

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "complaint"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omics
    -0.73
    ryu
    -0.71
     Kop
    -0.70
    scl
    -0.68
    hei
    -0.68
    keys
    -0.66
    unin
    -0.65
    ãĥĺ
    -0.63
    atomic
    -0.63
     Spawn
    -0.63
    POSITIVE LOGITS
     complaint
    3.68
     complaints
    2.50
     complain
    1.92
     grievance
    1.90
     complainant
    1.81
     Compl
    1.77
     accusation
    1.65
     allegation
    1.60
     complaining
    1.59
     lawsuit
    1.57
    Activations Density 0.011%

    No Known Activations