© 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. 13824
    Prev
    Next
    INDEX
    Explanations

    Roman numerals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the acronym "IX" and related terms

    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
    ffen
    -0.79
    aff
    -0.76
    offer
    -0.75
    itation
    -0.74
    actor
    -0.73
    stroke
    -0.72
    hm
    -0.72
    hra
    -0.70
    rill
    -0.69
    ida
    -0.69
    POSITIVE LOGITS
    TERN
    1.20
    URE
    1.09
    URES
    1.09
    IAL
    1.05
    IX
    1.05
    TY
    1.05
    NING
    1.03
    ATIVE
    1.03
    CLUS
    1.02
    VEN
    1.01
    Activations Density 0.018%

    No Known Activations