© 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. 0-RES-JB
    11. 15533
    Prev
    Next
    INDEX
    Explanations

    references to specific placements or positioning in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "placement" and related forms in various contexts

    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
    ibus
    -0.78
    ãĥ£
    -0.71
    ews
    -0.71
    jah
    -0.67
     Bern
    -0.67
    deen
    -0.66
    afi
    -0.66
    ires
    -0.65
    ********
    -0.64
    qv
    -0.64
    POSITIVE LOGITS
     placement
    4.02
     plac
    1.66
     positioning
    1.66
     placing
    1.65
    acement
    1.64
     relocation
    1.24
     insertion
    1.22
     arrangement
    1.21
     spacing
    1.18
     removal
    1.17
    Activations Density 0.009%

    No Known Activations