© 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. 3-RES-JB
    11. 539
    Prev
    Next
    INDEX
    Explanations

    resources or services related to mental health and community support

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the provision of resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Thumbnail
    -0.71
     IRA
    -0.65
    iaries
    -0.63
     Honor
    -0.63
     Zeal
    -0.62
     419
    -0.61
    berus
    -0.61
    owed
    -0.60
    426
    -0.60
    ItemTracker
    -0.59
    POSITIVE LOGITS
    LINE
    0.71
     steam
    0.71
    SpaceEngineers
    0.69
    steam
    0.67
    Hi
    0.65
    legraph
    0.64
    oller
    0.64
    onyms
    0.62
    volt
    0.61
     WORLD
    0.61
    Activations Density 0.000%

    No Known Activations