© 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. 10-RES-JB
    11. 9882
    Prev
    Next
    INDEX
    Explanations

    common phrases and sentence structures that involve hypothetical situations, plans, and thoughts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating permission or conditions for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constituted
    -0.74
     deteriorated
    -0.72
     subjected
    -0.72
     inhibited
    -0.72
     inaccur
    -0.71
     errone
    -0.71
     differed
    -0.69
     persisted
    -0.68
     incorrectly
    -0.68
     undermined
    -0.67
    POSITIVE LOGITS
     hopefully
    1.31
     someday
    1.16
    maybe
    1.16
    Hopefully
    1.13
     preferably
    1.12
     Hopefully
    1.11
    morrow
    1.09
     haha
    1.07
     yeah
    1.06
    laughs
    1.02
    Activations Density 0.395%

    No Known Activations