© 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. 0-RES-JB
    11. 18243
    Prev
    Next
    INDEX
    Explanations

    references to groups or organizations with the word 'ERS' in their names

    oai_token-act-pair · gpt-3.5-turbo

    words indicating various types of performers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quot
    -0.71
     imm
    -0.63
     abundance
    -0.61
     warp
    -0.60
     fact
    -0.58
     mash
    -0.57
     adm
    -0.57
     adam
    -0.56
     displacement
    -0.55
     mating
    -0.55
    POSITIVE LOGITS
    ERS
    4.18
    ER
    2.14
    ers
    1.99
    ORS
    1.65
    erers
    1.56
    ARS
    1.54
    ERY
    1.53
    ERSON
    1.49
    ership
    1.47
    EMS
    1.46
    Activations Density 0.009%

    No Known Activations