© 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. 6069
    Prev
    Next
    INDEX
    Explanations

    proper nouns or mentions of specific entities, such as names of companies, organizations, or titles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the"

    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
     beforehand
    -0.82
    /"
    -0.76
    iod
    -0.73
    Ò
    -0.72
    omever
    -0.71
     thereby
    -0.70
    æ©
    -0.70
    SPONSORED
    -0.70
     without
    -0.67
     directly
    -0.67
    POSITIVE LOGITS
    resa
    1.51
    odore
    1.37
    oret
    1.31
     Latest
    1.07
    orem
    1.06
    ories
    1.04
    atre
    1.03
     Basics
    0.98
     easiest
    0.97
     latest
    0.94
    Activations Density 0.192%

    No Known Activations