© 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. 1839
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or tension

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sometimes" indicating conditional or situational contexts

    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
     ASAP
    -0.82
    udeb
    -0.78
     tomorrow
    -0.71
     Rehab
    -0.69
     tonight
    -0.68
     Assessment
    -0.66
     Dat
    -0.66
    ciation
    -0.65
     Bam
    -0.64
     Skies
    -0.64
    POSITIVE LOGITS
     downright
    0.98
     unconsciously
    0.89
     accidentally
    0.85
     inadvertently
    0.85
     overlooked
    0.85
     mistaken
    0.85
     subconscious
    0.84
     unintentionally
    0.84
     misplaced
    0.81
     glimps
    0.78
    Activations Density 0.336%

    No Known Activations