© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 1670
    Prev
    Next
    INDEX
    Explanations

    proper names starting or ending with 'ber'

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the word "Ber" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãħĭ
    -0.70
     respect
    -0.69
    ENDED
    -0.67
     Virtue
    -0.66
    URA
    -0.64
     pity
    -0.62
    qqa
    -0.62
    lihood
    -0.61
     perverse
    -0.61
    uras
    -0.60
    POSITIVE LOGITS
    culosis
    1.26
    keley
    1.21
    geon
    1.02
    wald
    1.01
    deen
    0.99
    ber
    0.95
    lin
    0.93
    netic
    0.91
    ding
    0.89
    gex
    0.89
    Activations Density 0.010%

    No Known Activations