© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 24064
    Prev
    Next
    INDEX
    Explanations

    words related to introductory phrases or salutations

    oai_token-act-pair · gpt-3.5-turbo

    colons and text structure indicating citations or attributions

    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
     adversaries
    -0.75
     ingred
    -0.71
    anes
    -0.70
    phabet
    -0.68
    resa
    -0.68
    cair
    -0.68
    ¥ŀ
    -0.66
    senal
    -0.66
     undermin
    -0.66
    quartered
    -0.65
    POSITIVE LOGITS
     âĨij
    1.24
     Originally
    0.96
    Show
    0.81
     Whilst
    0.76
     Interesting
    0.75
     Assuming
    0.75
     ][
    0.74
    Originally
    0.74
    UTC
    0.71
     Adding
    0.71
    Activations Density 0.081%

    No Known Activations