© 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. 11-RES-JB
    11. 1393
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms of various words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to specific entities or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omorphic
    -0.85
    hered
    -0.84
    cle
    -0.83
    zzle
    -0.82
    zing
    -0.79
    iform
    -0.77
    hers
    -0.76
    enberg
    -0.76
    sov
    -0.75
    chers
    -0.74
    POSITIVE LOGITS
    OX
    1.22
    IFT
    1.21
    Ps
    1.19
    ITH
    1.17
    IELD
    1.16
    IPS
    1.14
    BG
    1.13
    IN
    1.13
    EED
    1.12
    AMS
    1.12
    Activations Density 0.085%

    No Known Activations