© 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. 7500
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and governmental topics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of ellipses or sequential periods in text

    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
    ãĥģ
    -0.69
    mith
    -0.63
    å¼
    -0.62
    ãĥİ
    -0.60
    iked
    -0.59
     infl
    -0.59
     encl
    -0.59
    qt
    -0.56
    ="/
    -0.56
     snap
    -0.55
    POSITIVE LOGITS
     ."
    0.88
    mil
    0.83
    actionDate
    0.81
    ################################
    0.76
    asers
    0.73
    selves
    0.71
    Ku
    0.70
    -.
    0.69
    resp
    0.68
    certain
    0.68
    Activations Density 0.021%

    No Known Activations