© 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. 2690
    Prev
    Next
    INDEX
    Explanations

    advertisement content within the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of advertisements

    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
    ties
    -0.69
    Ļ½
    -0.65
     makeshift
    -0.63
     perspect
    -0.63
    mate
    -0.62
    graded
    -0.60
     retri
    -0.60
    fulness
    -0.58
     wound
    -0.58
     contingent
    -0.58
    POSITIVE LOGITS
     Continue
    1.00
     Advertisement
    0.97
    advertisement
    0.80
    Advertisement
    0.72
    Skip
    0.71
    usercontent
    0.70
    Credit
    0.68
    ieu
    0.68
    ADVERTISEMENT
    0.67
    sburg
    0.67
    Activations Density 0.026%

    No Known Activations