© 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. 2369
    Prev
    Next
    INDEX
    Explanations

    phrases indicating some form of responsibility or obligation

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the article "a" in various contexts

    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
    anism
    -0.75
    steps
    -0.69
    an
    -0.68
    inel
    -0.67
    ATS
    -0.66
    iments
    -0.66
    Anim
    -0.65
    OWS
    -0.65
     entrants
    -0.65
     onlook
    -0.64
    POSITIVE LOGITS
     tendency
    1.41
     knack
    1.39
     penchant
    1.27
     propensity
    1.21
     chance
    1.21
     lot
    1.17
     reputation
    1.13
     vested
    1.07
     bunch
    0.99
     definite
    0.98
    Activations Density 0.175%

    No Known Activations