© 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. 9634
    Prev
    Next
    INDEX
    Explanations

    mentions of specific events or actions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods at the end of sentences

    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
     mur
    -0.71
     quir
    -0.66
     footing
    -0.65
     purse
    -0.62
     healer
    -0.59
     unden
    -0.58
     rod
    -0.58
     helper
    -0.58
     gaze
    -0.57
     quickest
    -0.57
    POSITIVE LOGITS
     Additionally
    1.21
     Needless
    1.19
     Similarly
    1.18
     Likewise
    1.13
     Moreover
    1.11
     Furthermore
    1.10
     Meanwhile
    1.08
     Ultimately
    1.07
     Consequently
    1.07
     Conversely
    1.06
    Activations Density 1.296%

    No Known Activations