© 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. 7-RES-JB
    11. 12597
    Prev
    Next
    INDEX
    Explanations

    words related to specificity or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that specify manner, degree, or area of focus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebus
    -0.70
    erest
    -0.67
    natureconservancy
    -0.65
    cock
    -0.64
     Mane
    -0.61
    orio
    -0.60
     Tackle
    -0.59
     overtake
    -0.59
    oren
    -0.59
     Divinity
    -0.56
    POSITIVE LOGITS
     by
    1.01
    ãĤ´ãĥ³
    0.92
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.86
    ãĥ¼ãĥ³
    0.81
    by
    0.80
     ILCS
    0.77
    Downloadha
    0.75
    through
    0.70
    BuyableInstoreAndOnline
    0.68
     srfAttach
    0.66
    Activations Density 0.416%

    No Known Activations