© 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. 8-RES-JB
    11. 7049
    Prev
    Next
    INDEX
    Explanations

    phrases related to hierarchical structures or systems

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to hierarchical structures and levels, particularly in the context of ladders or rankings

    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
    ivity
    -0.86
    terson
    -0.76
    sburg
    -0.76
    ivities
    -0.74
    tes
    -0.69
    iveness
    -0.69
    tan
    -0.69
    reb
    -0.67
    onom
    -0.66
    arella
    -0.66
    POSITIVE LOGITS
    xual
    1.02
     ladder
    0.90
     hierarchy
    0.84
     tiers
    0.82
     descent
    0.81
     precedence
    0.79
    MpServer
    0.77
     caste
    0.75
     stairs
    0.74
    stairs
    0.72
    Activations Density 0.089%

    No Known Activations