© 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. 6-RES-JB
    11. 5034
    Prev
    Next
    INDEX
    Explanations

    phrases that express positive sentiment or approval

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the," indicating a focus on definite references or common nouns in the text

    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
     according
    -0.74
    imi
    -0.73
    inel
    -0.71
     thereby
    -0.69
    Ò
    -0.69
     voluntarily
    -0.68
    âĦ¢:
    -0.68
     âĢº
    -0.67
    âĢł
    -0.67
    ashington
    -0.66
    POSITIVE LOGITS
    oret
    1.50
     easiest
    1.26
     simplest
    1.24
     downside
    1.21
     biggest
    1.21
     slightest
    1.13
    resa
    1.10
     hardest
    1.08
     brightest
    1.08
     quickest
    1.07
    Activations Density 0.573%

    No Known Activations