© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 8772
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical terms, abbreviations, and acronyms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal, ethical, and bureaucratic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itone
    -0.82
    udeb
    -0.79
    utch
    -0.79
    owler
    -0.77
    hiba
    -0.77
    sharp
    -0.75
    ichita
    -0.75
    alys
    -0.73
    hex
    -0.73
    ibel
    -0.72
    POSITIVE LOGITS
    LY
    1.62
    ING
    1.39
     OF
    1.39
    URE
    1.36
    HEAD
    1.35
    IES
    1.34
    IAL
    1.32
    MENT
    1.32
    URES
    1.31
    ONS
    1.31
    Activations Density 0.107%

    No Known Activations