© 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. 6-RES-JB
    11. 12888
    Prev
    Next
    INDEX
    Explanations

    medical terms related to body parts and functions

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical data and references related to surveys or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aband
    -0.59
    ="#
    -0.54
    Ô
    -0.54
    ameless
    -0.53
    ishable
    -0.53
    ãĤ°
    -0.53
    ought
    -0.51
    Knight
    -0.49
     sticky
    -0.49
    alien
    -0.49
    POSITIVE LOGITS
     respectively
    1.74
     alike
    1.15
    +.
    0.97
     thereof
    0.92
     attRot
    0.91
    depending
    0.85
    )).
    0.85
    .[
    0.84
     depending
    0.83
     thereafter
    0.82
    Activations Density 0.926%

    No Known Activations