© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 12203
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "This."

    oai_token-act-pair · gpt-3.5-turbo

    the word "This" and similar demonstrative pronouns, indicating a focus on specific statements or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     goto
    -0.63
     Reef
    -0.57
     etc
    -0.55
     sinful
    -0.54
    lbs
    -0.51
     lbs
    -0.51
     mans
    -0.51
     Oo
    -0.51
    CVE
    -0.51
     pounds
    -0.50
    POSITIVE LOGITS
    [/
    0.88
    odore
    0.81
    withstanding
    0.80
    ulty
    0.79
    jriwal
    0.79
    anmar
    0.78
    estine
    0.78
    vernment
    0.78
    rimination
    0.76
    usterity
    0.75
    Activations Density 0.252%

    No Known Activations