© 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. 10-RES-JB
    11. 12867
    Prev
    Next
    INDEX
    Explanations

    words related to formatting and structure in text and the concept of different options or choices

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting characters within the text

    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
     Glac
    -0.74
     glac
    -0.64
     1920
    -0.62
     sixty
    -0.62
     shotguns
    -0.60
     hurd
    -0.59
     960
    -0.59
     fifty
    -0.58
    ãĥķãĤ©
    -0.58
     retard
    -0.57
    POSITIVE LOGITS
    3
    1.34
     3
    1.13
    Third
    1.04
     Third
    1.00
     III
    0.98
    iii
    0.93
    333
    0.92
    III
    0.92
     iii
    0.90
    third
    0.90
    Activations Density 0.113%

    No Known Activations