© 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. 4-RES-JB
    11. 20855
    Prev
    Next
    INDEX
    Explanations

    phrases introduced by 'i.e.' - Latin abbreviation for "id est," which means "that is" or "in other words."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'e' in various contexts

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

    No Comments

    Negative Logits
    ingham
    -0.65
    Crunch
    -0.65
     PAL
    -0.62
    sb
    -0.62
     Finger
    -0.61
    adobe
    -0.60
    Streamer
    -0.59
    MSN
    -0.58
    iets
    -0.58
     rebate
    -0.57
    POSITIVE LOGITS
    gypt
    0.93
    clair
    0.87
    astern
    0.87
    etus
    0.86
    lements
    0.83
    resp
    0.82
    viously
    0.82
    clips
    0.82
    ldom
    0.81
    lez
    0.81
    Activations Density 0.016%

    No Known Activations