© 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. 22574
    Prev
    Next
    INDEX
    Explanations

    mentions of futuristic concepts or technologies

    oai_token-act-pair · gpt-3.5-turbo

    punctuation that signifies the end of 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
     inclusion
    -0.77
    ominated
    -0.73
     interchange
    -0.72
     imperson
    -0.72
     reb
    -0.71
    burgh
    -0.71
     involuntary
    -0.68
     systematically
    -0.68
     nonexistent
    -0.68
     representation
    -0.68
    POSITIVE LOGITS
    <|endoftext|>
    1.69
     ®
    1.43
     Hopefully
    1.40
     Until
    1.22
     Regardless
    1.16
     Stay
    1.15
     Otherwise
    1.14
     UPDATE
    1.12
     ;)
    1.09
     Unless
    1.08
    Activations Density 0.477%

    No Known Activations