© 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. 4-RES-JB
    11. 3633
    Prev
    Next
    INDEX
    Explanations

    dates in the format of year followed by a non-zero activation value

    oai_token-act-pair · gpt-3.5-turbo

    specific years or dates

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

    No Comments

    Negative Logits
     noisy
    -0.69
    ythm
    -0.65
    ¿½
    -0.64
     endless
    -0.63
    ongh
    -0.62
     plur
    -0.62
     citiz
    -0.62
    onite
    -0.62
    und
    -0.61
     multic
    -0.60
    POSITIVE LOGITS
     UTC
    0.81
     partName
    0.75
    âĶĢ
    0.75
     Referred
    0.75
    raq
    0.69
     |--
    0.68
     Dodge
    0.68
     Apply
    0.68
     ·
    0.68
     RELEASE
    0.67
    Activations Density 0.065%

    No Known Activations