© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4891
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a sense of certainty or confidence

    oai_token-act-pair · gpt-3.5-turbo

    the word "even."

    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
    rend
    -0.89
    asus
    -0.87
    aim
    -0.78
    cel
    -0.76
    ugal
    -0.76
    uble
    -0.74
    scribe
    -0.74
    othy
    -0.72
    acker
    -0.71
    isal
    -0.70
    POSITIVE LOGITS
     though
    1.25
     tho
    1.05
     remotely
    0.85
    handedly
    0.83
    handed
    0.81
     worse
    0.75
    though
    0.71
     if
    0.70
     mentioning
    0.70
     bothering
    0.70
    Activations Density 0.047%

    No Known Activations