© 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. 9-RES-JB
    11. 3243
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty and ambiguity

    oai_token-act-pair · gpt-3.5-turbo

    sentences expressing belief or optimism about a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     certific
    -0.83
     testified
    -0.77
     commented
    -0.69
    mentioned
    -0.67
     objected
    -0.67
     sacrific
    -0.65
     quoted
    -0.65
     Palest
    -0.65
    IGN
    -0.64
     narrated
    -0.63
    POSITIVE LOGITS
     finally
    1.10
     unstoppable
    0.95
     destined
    0.90
     poised
    0.90
     imminent
    0.86
     doomed
    0.84
     ripe
    0.84
    inx
    0.84
     breakthrough
    0.84
     doom
    0.83
    Activations Density 0.517%

    No Known Activations