© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8515
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "In the" followed by further content encompassing various topics

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" in varying frequencies

    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
    itiz
    -0.76
    ional
    -0.72
    tracks
    -0.66
    him
    -0.64
    irds
    -0.64
    enough
    -0.64
    ulner
    -0.64
    abel
    -0.64
    #$
    -0.63
    track
    -0.63
    POSITIVE LOGITS
     meantime
    1.73
     midst
    1.33
     absence
    1.29
     aftermath
    1.27
     wake
    1.12
     case
    1.12
     ensuing
    1.04
     past
    1.00
     meanwhile
    0.99
     intervening
    0.99
    Activations Density 0.130%

    No Known Activations