© 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. 14700
    Prev
    Next
    INDEX
    Explanations

    descriptions of time periods or durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe large quantities or significant events over time

    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
     cleaners
    -0.81
     sqor
    -0.81
     Cosponsors
    -0.74
     brakes
    -0.70
     Logged
    -0.66
    Downloadha
    -0.66
    theless
    -0.65
    trak
    -0.65
    awi
    -0.64
    ummies
    -0.64
    POSITIVE LOGITS
     universe
    0.74
     millennium
    0.73
    ylon
    0.73
     continuum
    0.71
     realm
    0.69
     spectrum
    0.68
     adolescence
    0.68
    ifice
    0.68
    thood
    0.67
    ggle
    0.67
    Activations Density 0.596%

    No Known Activations