© 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. 12869
    Prev
    Next
    INDEX
    Explanations

    years mentioned in a specific format, such as "from XXXX" with a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    specific years and durations related to historical events or time periods

    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
    ĺħ
    -0.61
     multip
    -0.61
     Trop
    -0.55
    rored
    -0.52
    needed
    -0.50
    ACTION
    -0.50
     cryst
    -0.50
    ATHER
    -0.50
     favor
    -0.48
     Nature
    -0.48
    POSITIVE LOGITS
     onwards
    1.61
     onward
    1.55
     until
    1.25
     till
    1.20
    until
    1.09
     through
    0.94
     downwards
    0.88
    til
    0.86
     inception
    0.84
     til
    0.83
    Activations Density 0.082%

    No Known Activations