© 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. 7-RES-JB
    11. 3203
    Prev
    Next
    INDEX
    Explanations

    phrases indicating likelihood or frequency

    oai_token-act-pair · gpt-3.5-turbo

    recurrent patterns indicating typicality or frequency of occurrence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    htaking
    -0.78
    atures
    -0.78
    iates
    -0.73
    jab
    -0.71
    ATS
    -0.71
    ancer
    -0.71
    chell
    -0.69
    ati
    -0.69
    elong
    -0.65
    arta
    -0.65
    POSITIVE LOGITS
    entimes
    1.17
     referred
    0.90
     accompanied
    0.89
     consist
    0.88
     overlooked
    0.85
     involve
    0.84
     encountered
    0.83
     preceded
    0.82
     vary
    0.81
     abbrevi
    0.80
    Activations Density 0.182%

    No Known Activations