© 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. 10071
    Prev
    Next
    INDEX
    Explanations

    terms related to methods, procedures, or systems

    oai_token-act-pair · gpt-3.5-turbo

    references to various methods or methodologies

    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
    hips
    -0.75
    mares
    -0.74
    âĢİ
    -0.71
    leased
    -0.67
    erves
    -0.66
    itizens
    -0.65
    uries
    -0.64
    ropolitan
    -0.64
    anke
    -0.64
    MSN
    -0.63
    POSITIVE LOGITS
     method
    3.46
     Method
    2.64
    method
    2.61
     methods
    2.60
    Method
    2.28
     methodology
    2.04
     Methods
    2.03
     technique
    1.98
    METHOD
    1.93
    Methods
    1.77
    Activations Density 0.008%

    No Known Activations