© 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. 2766
    Prev
    Next
    INDEX
    Explanations

    phrases expressing certainty or high probability

    oai_token-act-pair · gpt-3.5-turbo

    emphasizing adverbs that convey certainty or intensity

    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
    iling
    -0.67
    archment
    -0.63
    dding
    -0.62
     attempting
    -0.62
    oller
    -0.62
     guiActiveUnfocused
    -0.61
    Calling
    -0.61
    Warning
    -0.61
    senal
    -0.60
     Reporting
    -0.60
    POSITIVE LOGITS
     happened
    1.22
     happens
    1.13
     hurts
    1.07
     transpired
    1.06
     feels
    1.05
     seems
    1.04
     occurred
    1.01
     boils
    1.00
     seemed
    0.98
     took
    0.98
    Activations Density 0.118%

    No Known Activations