© 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. 9-RES-JB
    11. 8986
    Prev
    Next
    INDEX
    Explanations

    sentences ending in full stops or question marks followed by words relating to beliefs or assumptions

    oai_token-act-pair · gpt-3.5-turbo

    punctuated sentences that may indicate conclusions or endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascus
    -0.90
     earthqu
    -0.85
     teasp
    -0.80
     eleph
    -0.77
     exting
    -0.76
    quartered
    -0.73
    ensable
    -0.72
     concess
    -0.71
    isbury
    -0.71
    oppable
    -0.70
    POSITIVE LOGITS
     Either
    1.89
     Maybe
    1.82
     Regardless
    1.74
     Perhaps
    1.72
     Anyway
    1.68
     Possibly
    1.67
     Alternatively
    1.66
     Whatever
    1.57
    Either
    1.55
     Probably
    1.52
    Activations Density 0.440%

    No Known Activations