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

    Neuronpedia

    Jacobian LensNEW
    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. 20839
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of solidarity or shared experience

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "alone" and related phrases indicating solitude or lack of support

    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
    imal
    -0.70
     GENERAL
    -0.69
    VERTISEMENT
    -0.65
    inders
    -0.64
    ffff
    -0.64
    mun
    -0.62
     decay
    -0.61
    chlor
    -0.61
    wash
    -0.60
    mit
    -0.59
    POSITIVE LOGITS
    arus
    0.79
     culp
    0.71
    odox
    0.67
     academ
    0.66
    ta
    0.65
    gebra
    0.64
     exoner
    0.63
     apprehens
    0.63
    isSpecialOrderable
    0.62
    MpServer
    0.61
    Activations Density 0.020%

    No Known Activations