© 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. 3-RES-JB
    11. 311
    Prev
    Next
    INDEX
    Explanations

    terms related to physical or medical conditions, especially those involving the suffix "-ural"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "postural" or "posture" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tower
    -0.75
    KEN
    -0.71
    arette
    -0.70
    sters
    -0.70
    orious
    -0.69
    INS
    -0.68
    enthal
    -0.68
    onen
    -0.66
     Finder
    -0.66
    racuse
    -0.65
    POSITIVE LOGITS
    idad
    0.98
    ized
    0.84
    ities
    0.81
    tarians
    0.80
    ural
    0.78
    ization
    0.77
     vibrations
    0.77
    istic
    0.76
    ism
    0.75
    tarian
    0.75
    Activations Density 0.008%

    No Known Activations