© 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. 9018
    Prev
    Next
    INDEX
    Explanations

    phrases related to newsletters or articles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ERS" 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
     Bed
    -0.66
    spe
    -0.66
     reinforcement
    -0.65
    ãĥĥ
    -0.65
    ãĥĥãĤ¯
    -0.65
     Chak
    -0.63
    steel
    -0.60
     Persian
    -0.60
     Sop
    -0.59
     san
    -0.59
    POSITIVE LOGITS
    VILLE
    1.09
    poons
    1.07
    hip
    1.06
    IAL
    1.05
    FIELD
    1.05
    BUR
    1.04
    ELF
    1.03
    HAM
    0.99
    hips
    0.97
    cream
    0.96
    Activations Density 0.008%

    No Known Activations