© 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. 6442
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical sensations and impacts on mood

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with official approval or designation

    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
    pak
    -0.75
     unfocusedRange
    -0.74
    uyomi
    -0.74
    TN
    -0.71
    aukee
    -0.70
    asca
    -0.70
    FTWARE
    -0.69
    Contribut
    -0.68
    assad
    -0.67
    lyak
    -0.66
    POSITIVE LOGITS
    SPONSORED
    0.86
    killer
    0.68
     Huck
    0.68
    safe
    0.67
    wave
    0.67
    cean
    0.65
    oca
    0.64
    isted
    0.62
     printers
    0.61
    fields
    0.59
    Activations Density 0.000%

    No Known Activations