© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7384
    Prev
    Next
    INDEX
    Explanations

    instances of words related to assisting, helping or making things easier

    oai_token-act-pair · gpt-3.5-turbo

    terms related to enabling or helping processes

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

    No Comments

    Negative Logits
    shit
    -0.76
    bane
    -0.73
    kar
    -0.71
    den
    -0.69
    bur
    -0.69
    ander
    -0.67
    guy
    -0.66
    man
    -0.66
    thing
    -0.66
    boy
    -0.64
    POSITIVE LOGITS
     facilitating
    0.96
     facilitate
    0.88
     facilit
    0.80
    ilitation
    0.79
    folios
    0.78
     facilitates
    0.77
     facilitated
    0.76
    ances
    0.74
    folio
    0.71
     communication
    0.70
    Activations Density 0.020%

    No Known Activations