© 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. 7-RES-JB
    11. 22731
    Prev
    Next
    INDEX
    Explanations

    phrases related to emphasis or direction within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include qualifiers or expressions of frequency and certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    indal
    -0.85
    ptives
    -0.75
    ampions
    -0.74
    estern
    -0.73
    skirts
    -0.72
    lees
    -0.70
    ates
    -0.67
    FTWARE
    -0.67
    izon
    -0.66
    chin
    -0.65
    POSITIVE LOGITS
     guessed
    0.73
     anecd
    0.70
     paraph
    0.67
     Rasm
    0.64
     fung
    0.64
     Cth
    0.64
     helicop
    0.57
     plaus
    0.56
     correctness
    0.56
     transact
    0.55
    Activations Density 0.281%

    No Known Activations