© 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. 2458
    Prev
    Next
    INDEX
    Explanations

    words related to rocks or rocky terrain

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "ock" and its variations in different contexts

    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
     pregn
    -0.76
     glim
    -0.67
     simultane
    -0.66
     Debor
    -0.64
    pard
    -0.63
     trave
    -0.63
     exha
    -0.63
    orescence
    -0.62
     apprehension
    -0.61
    undai
    -0.60
    POSITIVE LOGITS
    strap
    1.18
    warm
    0.94
    roach
    0.91
    ers
    0.89
    stra
    0.88
    yards
    0.87
    heimer
    0.85
    erman
    0.85
    tails
    0.85
    tail
    0.82
    Activations Density 0.042%

    No Known Activations