© 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. 0-RES-JB
    11. 19324
    Prev
    Next
    INDEX
    Explanations

    items listed numerically or categorically

    oai_token-act-pair · gpt-3.5-turbo

    references to lists, particularly in the context of enumerating items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     irrigation
    -0.63
     overtime
    -0.63
     daylight
    -0.61
     gy
    -0.61
     tears
    -0.60
     fertil
    -0.60
     sew
    -0.59
     inclined
    -0.59
     Strikes
    -0.59
     circumcised
    -0.57
    POSITIVE LOGITS
    list
    4.15
    lists
    3.05
    LIST
    2.72
    listed
    2.30
    List
    2.30
     LIST
    2.22
     List
    2.21
     list
    2.03
     Lists
    1.88
     lists
    1.68
    Activations Density 0.018%

    No Known Activations