© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12521
    Prev
    Next
    INDEX
    Explanations

    comparative expressions indicating similarity or equivalence

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases or constructions expressing similarity

    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
    WAYS
    -0.70
    Leaks
    -0.70
     Versus
    -0.65
    ASE
    -0.63
    MORE
    -0.63
     Limits
    -0.61
    ASED
    -0.60
    rises
    -0.60
     Specifications
    -0.58
    ALLY
    -0.58
    POSITIVE LOGITS
    pired
    1.12
    pires
    1.05
    phy
    1.01
    ym
    0.99
     follows
    0.88
    ocial
    0.87
    leep
    0.85
    pire
    0.84
     close
    0.83
    ynchron
    0.83
    Activations Density 0.066%

    No Known Activations