© 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. 9499
    Prev
    Next
    INDEX
    Explanations

    words related to planning and scheming

    oai_token-act-pair · gpt-3.5-turbo

    terms related to imaginations and related themes

    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
     patch
    -0.72
     Full
    -0.68
     full
    -0.65
     plank
    -0.65
     fork
    -0.64
    aker
    -0.63
     grade
    -0.63
     Electronic
    -0.62
    AMA
    -0.61
     bip
    -0.61
    POSITIVE LOGITS
    inations
    4.33
    inates
    1.47
    inatory
    1.45
    ination
    1.44
    ineries
    1.43
    inators
    1.41
    inating
    1.23
    inate
    1.17
    inator
    1.14
    iances
    1.10
    Activations Density 0.022%

    No Known Activations