© 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. 10-RES-JB
    11. 11056
    Prev
    Next
    INDEX
    Explanations

    descriptions of legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong emotional responses or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Additionally
    -1.02
    Conclusion
    -0.96
    Furthermore
    -0.92
    Firstly
    -0.90
    Recommend
    -0.90
    Secondly
    -0.89
    Therefore
    -0.89
     Whilst
    -0.87
    Regarding
    -0.87
     [/
    -0.86
    POSITIVE LOGITS
     mornings
    1.07
     strangers
    1.03
     dusk
    0.97
     adolescence
    0.96
     smiles
    0.93
     startled
    0.88
     greets
    0.87
     twent
    0.87
     passers
    0.84
     perched
    0.83
    Activations Density 0.829%

    No Known Activations