© 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. 19255
    Prev
    Next
    INDEX
    Explanations

    time-related information such as dates, years, and specific periods

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics

    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
     ransom
    -0.72
     motives
    -0.66
     motivations
    -0.65
    bol
    -0.64
     advers
    -0.63
     suggestion
    -0.63
    seek
    -0.62
     purposes
    -0.61
     invests
    -0.61
     advoc
    -0.60
    POSITIVE LOGITS
    enough
    0.81
     exhausted
    0.81
    ettel
    0.77
    naissance
    0.75
    hn
    0.73
    sett
    0.71
    ©¶æ¥µ
    0.71
    thirds
    0.70
    stasy
    0.69
    apsed
    0.68
    Activations Density 0.204%

    No Known Activations