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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12606
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to different stages or phases of processes

    oai_token-act-pair · gpt-3.5-turbo

    references to various stages of processes or developments

    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
    ctuary
    -0.65
    osponsors
    -0.65
    osher
    -0.64
    rist
    -0.64
    cup
    -0.63
     Picks
    -0.63
    onyms
    -0.63
    ews
    -0.62
    aver
    -0.61
    ores
    -0.60
    POSITIVE LOGITS
     development
    0.98
     unfold
    0.92
     evolution
    0.91
     completion
    0.88
     digestion
    0.88
     negotiations
    0.88
     proceedings
    0.88
     elimination
    0.86
     transition
    0.85
     transformation
    0.85
    Activations Density 0.164%

    No Known Activations