© 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. 13934
    Prev
    Next
    INDEX
    Explanations

    the surname "Short" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Short" in various 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
    ILLE
    -0.84
    itational
    -0.82
    ICAN
    -0.81
    äºĶ
    -0.70
    VERTIS
    -0.69
    Magikarp
    -0.68
    igators
    -0.67
    risome
    -0.67
    IENCE
    -0.67
    ITNESS
    -0.65
    POSITIVE LOGITS
    ened
    1.03
    comings
    1.02
    short
    1.00
    cuts
    0.94
    ening
    0.90
    ens
    0.84
    sword
    0.82
    cut
    0.82
    bread
    0.82
    ness
    0.81
    Activations Density 0.009%

    No Known Activations