© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2833
    Prev
    Next
    INDEX
    Explanations

    words related to specific dates or times

    oai_token-act-pair · gpt-3.5-turbo

    temporal or conditional phrases

    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
     shedding
    -0.70
     slowing
    -0.70
     shock
    -0.69
     invasion
    -0.68
     infiltration
    -0.67
     rental
    -0.67
     stride
    -0.66
     envy
    -0.66
     prone
    -0.66
     infiltr
    -0.66
    POSITIVE LOGITS
    Else
    1.06
    Us
    0.92
     Things
    0.86
    Measure
    0.84
    Mine
    0.83
     Lives
    0.83
     Places
    0.83
    Different
    0.83
    Own
    0.81
    humans
    0.80
    Activations Density 0.170%

    No Known Activations