© 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. 8-RES-JB
    11. 11649
    Prev
    Next
    INDEX
    Explanations

    references to independence or things that are independent

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "independent" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mers
    -0.98
    itual
    -0.97
    frey
    -0.80
    amac
    -0.77
    efully
    -0.75
    ttp
    -0.74
     Nieto
    -0.74
    eful
    -0.74
    older
    -0.74
    days
    -0.74
    POSITIVE LOGITS
     contractor
    1.16
     minded
    1.03
     contractors
    1.01
     thinker
    0.90
     expenditure
    0.84
     counsel
    0.82
     verification
    0.81
     judiciary
    0.81
     observer
    0.75
     thinkers
    0.74
    Activations Density 0.036%

    No Known Activations