© 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. 8611
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific cultural or entertainment figures and related terms

    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
    apego
    -0.66
    DJ
    -0.62
     bluff
    -0.61
    ient
    -0.60
    ahi
    -0.59
    acists
    -0.58
    orer
    -0.58
    oths
    -0.58
    raper
    -0.57
    rehensive
    -0.57
    POSITIVE LOGITS
     guise
    1.16
     increments
    1.11
     mode
    1.01
     fashion
    0.96
     contexts
    0.96
     manner
    0.95
     vein
    0.93
     circles
    0.91
     vicinity
    0.90
     nutshell
    0.86
    Activations Density 1.034%

    No Known Activations