© 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. 2-RES-JB
    11. 12769
    Prev
    Next
    INDEX
    Explanations

    instances where one option or action is preferred over another

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "instead."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cision
    -0.72
    ongo
    -0.71
    mud
    -0.67
    fried
    -0.65
    lees
    -0.64
    raz
    -0.64
    anon
    -0.64
    minent
    -0.64
     Shake
    -0.63
    rament
    -0.63
    POSITIVE LOGITS
     opting
    0.88
     instead
    0.84
    instead
    0.80
     preferring
    0.70
     chose
    0.70
     opt
    0.68
     cannabin
    0.68
     opted
    0.67
     passively
    0.67
    artments
    0.67
    Activations Density 0.020%

    No Known Activations