© 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. 9614
    Prev
    Next
    INDEX
    Explanations

    phrases related to events happening a certain number of times

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to time, particularly repeated time references

    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
    haar
    -0.83
    krit
    -0.73
    anguage
    -0.73
    ennes
    -0.72
    aceous
    -0.71
    amera
    -0.71
    sterdam
    -0.70
    abase
    -0.70
    apesh
    -0.70
    CHAT
    -0.68
    POSITIVE LOGITS
    etheless
    0.79
     Bucc
    0.70
    teness
    0.70
     reigning
    0.64
    llor
    0.63
    foundland
    0.62
    ful
    0.60
     resident
    0.60
    æķ
    0.60
     veteran
    0.59
    Activations Density 0.015%

    No Known Activations