© 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. 17000
    Prev
    Next
    INDEX
    Explanations

    statements indicating future intentions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the modal verb "would."

    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
     Brilliant
    -0.62
    cius
    -0.62
     Pse
    -0.60
    uded
    -0.59
    RAM
    -0.59
    Building
    -0.58
     sqor
    -0.58
     dynamics
    -0.57
    ceived
    -0.57
    ancer
    -0.56
    POSITIVE LOGITS
     gladly
    1.04
     withhold
    0.98
     be
    0.97
     sue
    0.96
     continue
    0.94
     donate
    0.89
     seek
    0.88
     leave
    0.88
    soon
    0.88
     postpone
    0.87
    Activations Density 0.178%

    No Known Activations