© 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. 8934
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of "not just" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and the use of commas in complex sentences

    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
     Became
    -0.67
    Offline
    -0.64
     misunder
    -0.60
    OME
    -0.57
    aky
    -0.56
    MODE
    -0.54
    IER
    -0.54
    cellaneous
    -0.54
    VIS
    -0.54
    mx
    -0.54
    POSITIVE LOGITS
     nor
    1.63
    nor
    1.30
     Nor
    1.09
     anymore
    0.95
    although
    0.95
    Nor
    0.94
     Rather
    0.92
     though
    0.87
     but
    0.86
    yet
    0.84
    Activations Density 0.226%

    No Known Activations