© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6141
    Prev
    Next
    INDEX
    Explanations

    words related to keeping and maintaining something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express ongoing actions or states

    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
    KEN
    -0.75
    sonian
    -0.74
    externalActionCode
    -0.69
    KY
    -0.68
    atana
    -0.67
    orthy
    -0.67
    acus
    -0.66
    çīĪ
    -0.66
    illet
    -0.66
    haps
    -0.65
    POSITIVE LOGITS
     pace
    0.90
     tabs
    0.86
     popping
    0.85
     bothering
    0.83
     afloat
    0.83
     piling
    0.77
     reminding
    0.75
     churn
    0.73
     repeating
    0.72
     happening
    0.71
    Activations Density 0.051%

    No Known Activations