© 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. 2-RES-JB
    11. 12498
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names consisting of three uppercase letters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the abbreviation "GL" in various contexts

    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
    riad
    -0.64
     California
    -0.62
     Dele
    -0.61
    cles
    -0.61
    Rated
    -0.61
     Hiroshima
    -0.59
    chin
    -0.59
    taining
    -0.59
    cling
    -0.59
    raviolet
    -0.59
    POSITIVE LOGITS
    ength
    1.14
    ENN
    0.89
    OSS
    0.84
    OCK
    0.82
    FW
    0.82
    ossip
    0.82
    ibrary
    0.81
    ibr
    0.81
    ASS
    0.80
    TF
    0.79
    Activations Density 0.004%

    No Known Activations