© 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. 13657
    Prev
    Next
    INDEX
    Explanations

    technical terms related to hard and soft materials, likely in a context related to pressure or tension

    oai_token-act-pair · gpt-3.5-turbo

    references to challenges or difficulties, particularly in relation to "hard" and "soft" contrasts

    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
    Winged
    -0.72
    stanbul
    -0.67
    pty
    -0.65
    END
    -0.64
    inker
    -0.63
     Ming
    -0.63
    rev
    -0.62
     Canaver
    -0.62
    ifa
    -0.62
    ajo
    -0.62
    POSITIVE LOGITS
    Hard
    2.24
     Hard
    2.18
    hard
    2.03
     hard
    1.92
     Soft
    1.90
     soft
    1.85
    Soft
    1.82
     harder
    1.76
    soft
    1.75
     hardness
    1.73
    Activations Density 0.192%

    No Known Activations