© 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. 12585
    Prev
    Next
    INDEX
    Explanations

    words related to decision-making and action items

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and its associated context in relation to public issues

    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
    acca
    -0.75
    rand
    -0.72
    á¸
    -0.68
     suppose
    -0.67
    bear
    -0.64
    isan
    -0.64
    ventus
    -0.64
    ivas
    -0.63
    etsu
    -0.62
    pport
    -0.62
    POSITIVE LOGITS
     same
    1.20
     lowest
    1.08
     highest
    1.06
     confines
    1.03
     bloodstream
    1.00
     proverbial
    0.94
     entirety
    0.94
     shoulders
    0.92
     widest
    0.92
     forefront
    0.91
    Activations Density 0.422%

    No Known Activations