© 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. 2012
    Prev
    Next
    INDEX
    Explanations

    names starting with "els" and are followed by a combination of letters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "els" within words

    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
     Occupations
    -0.69
    ALLY
    -0.66
     citiz
    -0.65
     Seym
    -0.64
    spe
    -0.64
     Augusta
    -0.62
    acity
    -0.62
     dividend
    -0.61
    scribed
    -0.61
    ythm
    -0.60
    POSITIVE LOGITS
    inki
    1.10
    warm
    1.00
    bach
    0.99
    hof
    0.97
    pace
    0.91
    ong
    0.89
    ounge
    0.86
    kamp
    0.86
    ength
    0.84
    zeb
    0.82
    Activations Density 0.040%

    No Known Activations