© 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. 4-RES-JB
    11. 14452
    Prev
    Next
    INDEX
    Explanations

    adjectives related to texture and taste, particularly emphasizing a crunchy or firm quality

    oai_token-act-pair · gpt-3.5-turbo

    descriptions related to crispiness or clarity

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

    No Comments

    Negative Logits
    WAY
    -0.76
    akespe
    -0.65
    orc
    -0.63
    adder
    -0.60
    roit
    -0.60
    htar
    -0.60
    abuse
    -0.60
     Advoc
    -0.60
     Corinthians
    -0.59
    lex
    -0.59
    POSITIVE LOGITS
    acies
    0.96
    bread
    0.94
    aceous
    0.91
     crisp
    0.81
    adoes
    0.79
    stal
    0.79
    iness
    0.77
    meat
    0.77
     pancakes
    0.75
    ulate
    0.75
    Activations Density 0.010%

    No Known Activations