© 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. 9-RES-JB
    11. 5602
    Prev
    Next
    INDEX
    Explanations

    words related to camera features and photography

    oai_token-act-pair · gpt-3.5-turbo

    the word "of" and its variations in slightly different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Elves
    -0.71
     Bots
    -0.67
     Dahl
    -0.66
     Bal
    -0.66
     refrain
    -0.66
     Stra
    -0.66
     Slov
    -0.65
     Corpus
    -0.64
     Isles
    -0.63
    ĸļ
    -0.62
    POSITIVE LOGITS
    ound
    1.07
    otation
    0.94
    entric
    0.93
    imensional
    0.93
    uclear
    0.92
    pload
    0.91
    rame
    0.91
    ocus
    0.90
    atri
    0.90
    ocking
    0.90
    Activations Density 0.100%

    No Known Activations