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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 13548
    Prev
    Next
    INDEX
    Explanations

    phrases related to essential or core concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fundamental principles or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kers
    -0.79
    zzo
    -0.72
     Carbuncle
    -0.72
     Stall
    -0.69
    peak
    -0.66
    berman
    -0.66
     Leone
    -0.64
     Mouth
    -0.64
     Decker
    -0.63
     Lup
    -0.62
    POSITIVE LOGITS
     fundamental
    0.99
    amental
    0.96
     fundamentals
    0.86
     tenets
    0.83
     necessities
    0.83
     aspects
    0.83
     proble
    0.82
     liberties
    0.80
    gebra
    0.79
     principles
    0.78
    Activations Density 0.008%

    No Known Activations