© 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. 8-RES-JB
    11. 17097
    Prev
    Next
    INDEX
    Explanations

    random strings of characters and incomplete sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transformed
    -0.62
     guarantees
    -0.58
     respectively
    -0.58
    ModLoader
    -0.58
     multiplying
    -0.57
    staking
    -0.56
     increment
    -0.55
    imposed
    -0.54
     thereafter
    -0.53
    checked
    -0.53
    POSITIVE LOGITS
    ucl
    0.66
    é¾
    0.66
     Miscellaneous
    0.65
    ¶
    0.60
    window
    0.59
     franc
    0.57
     Xperia
    0.56
    ®
    0.56
     Sask
    0.56
     Cosponsors
    0.55
    Activations Density 0.303%

    No Known Activations