© 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. 6974
    Prev
    Next
    INDEX
    Explanations

    phrases or words indicating common occurrences or practices

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating prevalence or common practices within various 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
    appointed
    -0.68
    alion
    -0.67
    iris
    -0.67
    ileaks
    -0.65
     guessed
    -0.64
    inson
    -0.64
    CTV
    -0.63
     succeeded
    -0.63
    mouth
    -0.62
    ihad
    -0.62
    POSITIVE LOGITS
     contemporary
    0.93
     modern
    0.92
     Occupations
    0.91
     societies
    0.87
     Europe
    0.82
     Southeast
    0.81
     many
    0.77
     Scandinavian
    0.77
     Silicon
    0.75
    ORPG
    0.75
    Activations Density 0.281%

    No Known Activations