© 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. 4058
    Prev
    Next
    INDEX
    Explanations

    declarative sentences or fragments ending with punctuations like period/full stop

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey important information or statements

    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
     reversible
    -0.77
     masse
    -0.73
     calf
    -0.69
     stationary
    -0.68
    iency
    -0.68
     remission
    -0.68
     barric
    -0.67
    ierre
    -0.66
     extinguished
    -0.66
     hesitated
    -0.65
    POSITIVE LOGITS
     Its
    1.38
     Known
    1.23
     Yet
    1.20
     Moreover
    1.18
     Nevertheless
    1.18
     Additionally
    1.17
     Located
    1.16
     Nonetheless
    1.13
     However
    1.13
     Consequently
    1.13
    Activations Density 0.535%

    No Known Activations