© 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. 8-RES-JB
    11. 7915
    Prev
    Next
    INDEX
    Explanations

    actions or tasks that are attempted but not successful

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate action or change in state

    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
    eg
    -0.79
    ember
    -0.72
    mob
    -0.71
    eria
    -0.70
    Phys
    -0.68
    .?
    -0.68
    âĢij
    -0.68
    mp
    -0.66
    wow
    -0.66
    peg
    -0.65
    POSITIVE LOGITS
     aside
    0.69
    theless
    0.67
    ãĥ¥
    0.64
     nonetheless
    0.64
     unsus
    0.63
     instead
    0.59
    itely
    0.58
    =]
    0.57
     them
    0.57
     only
    0.57
    Activations Density 0.326%

    No Known Activations