© 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. 6-RES-JB
    11. 11597
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty or emphasis, such as 'always', 'probably', 'certainly'

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating certainty or continuity

    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
    core
    -0.68
    furt
    -0.67
     Mant
    -0.67
     Respons
    -0.67
    ylum
    -0.66
     Mats
    -0.65
     Mour
    -0.64
    Unity
    -0.62
    Lenin
    -0.61
     Wend
    -0.60
    POSITIVE LOGITS
     afford
    1.08
     withstand
    0.92
     imagine
    0.89
     conceive
    0.88
     communicate
    0.87
    ibly
    0.86
    apply
    0.86
    berra
    0.84
     rely
    0.83
    ivably
    0.83
    Activations Density 0.081%

    No Known Activations