© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10427
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something has exceeded a certain point or limit

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the concept of going "too far" in various contexts

    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
    itu
    -0.71
    ivari
    -0.69
    etta
    -0.66
    liction
    -0.65
    utt
    -0.64
    otte
    -0.64
    tu
    -0.63
    iku
    -0.62
     Puppet
    -0.62
     plots
    -0.61
    POSITIVE LOGITS
     differently
    0.76
     lengths
    0.76
     unnoticed
    0.73
     sidx
    0.69
     stride
    0.66
     onstage
    0.65
     Herz
    0.64
    Alexander
    0.63
     overboard
    0.62
    HER
    0.60
    Activations Density 0.054%

    No Known Activations