© 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. 2-RES-JB
    11. 9135
    Prev
    Next
    INDEX
    Explanations

    words related to halving or cutting in half

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "halting" or cessation

    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
    ULTS
    -0.90
    URE
    -0.81
    URES
    -0.77
     Provider
    -0.75
    æĸ¹
    -0.74
     Corpus
    -0.73
    é¾įå
    -0.73
     Cause
    -0.73
     Suite
    -0.70
     Orig
    -0.69
    POSITIVE LOGITS
    tering
    1.03
     hal
    1.02
    ftime
    1.00
    ifax
    0.99
    haul
    0.93
    ving
    0.92
    tered
    0.91
    ved
    0.89
    pless
    0.82
    ocaust
    0.82
    Activations Density 0.003%

    No Known Activations