© 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. 6-RES-JB
    11. 15277
    Prev
    Next
    INDEX
    Explanations

    phrases indicating action or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    instances of planning and decision-making

    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
     Digest
    -0.67
    Downloadha
    -0.62
     guiActiveUn
    -0.61
     himself
    -0.59
    oshenko
    -0.58
     herself
    -0.56
    Pain
    -0.55
     clipboard
    -0.55
    soever
    -0.53
     ///
    -0.52
    POSITIVE LOGITS
     ourselves
    1.63
     our
    0.88
    mble
    0.81
     ours
    0.79
     OUR
    0.75
     selves
    0.72
    assies
    0.72
     together
    0.69
    yg
    0.69
    ]."
    0.67
    Activations Density 0.773%

    No Known Activations