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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3350
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeds and gardening

    oai_token-act-pair · gpt-3.5-turbo

    references to digital media formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.78
    uliffe
    -0.71
     kinderg
    -0.67
    ICA
    -0.66
     interventions
    -0.63
    aceous
    -0.63
    izations
    -0.62
    Gaza
    -0.61
    FORE
    -0.60
     reusable
    -0.60
    POSITIVE LOGITS
    ds
    1.13
    ertodd
    0.88
    ubs
    0.87
    ument
    0.86
    plings
    0.85
    urance
    0.84
    fw
    0.84
    kies
    0.84
    orm
    0.84
    ync
    0.83
    Activations Density 0.006%

    No Known Activations