© 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. 2-RES-JB
    6. 12522
    Prev
    Next
    INDEX
    Explanations

    references to specific names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names and titles related to notable filmmakers and works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adesh
    -0.87
    estern
    -0.81
    orget
    -0.73
    enza
    -0.72
    imated
    -0.70
    onductor
    -0.70
    eas
    -0.69
    oran
    -0.69
    engers
    -0.68
    arro
    -0.67
    POSITIVE LOGITS
     Ridley
    0.89
    çĶŁ
    0.78
    fitting
    0.76
    inction
    0.75
    vid
    0.69
    etheus
    0.68
    href
    0.68
    xes
    0.67
     Skydragon
    0.64
    ModLoader
    0.63
    Activations Density 0.031%

    No Known Activations