© 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. 18607
    Prev
    Next
    INDEX
    Explanations

    dates or time-related information

    oai_token-act-pair · gpt-3.5-turbo

    instances of political references and events

    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
    ...)
    -0.96
    ++++++++++++++++
    -0.93
     =================
    -0.89
     :-)
    -0.76
    ynt
    -0.74
    ...?
    -0.73
     recognise
    -0.73
    ynthesis
    -0.73
    Reviewer
    -0.71
    ++++
    -0.70
    POSITIVE LOGITS
    ADVERTISEMENT
    0.90
     ÂŃ
    0.81
     Ivanka
    0.76
     ,"
    0.74
     POLITICO
    0.73
     lawmaker
    0.73
     Emanuel
    0.72
     Benghazi
    0.71
    GOP
    0.70
     Biden
    0.70
    Activations Density 0.135%

    No Known Activations