© 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. 3-RES-JB
    11. 10731
    Prev
    Next
    INDEX
    Explanations

    words related to water purification and treatment techniques

    oai_token-act-pair · gpt-3.5-turbo

    words related to processes and effects of desalinization

    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
    aver
    -0.77
    bie
    -0.67
    arag
    -0.64
    erous
    -0.63
    herty
    -0.62
    bies
    -0.62
    iddling
    -0.62
    mere
    -0.62
    MER
    -0.58
    LV
    -0.57
    POSITIVE LOGITS
    ysis
    0.98
    inate
    0.80
    rontal
    0.79
    ination
    0.74
    inated
    0.74
    itial
    0.74
    xual
    0.73
    htaking
    0.73
    jured
    0.72
    osate
    0.69
    Activations Density 0.026%

    No Known Activations