© 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. 24054
    Prev
    Next
    INDEX
    Explanations

    names containing "Jr" as a suffix

    oai_token-act-pair · gpt-3.5-turbo

    the abbreviation 'Jr' following a name, indicating a specific generational identifier

    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
    medium
    -0.72
    Front
    -0.71
    mitt
    -0.71
     Trend
    -0.70
    actionDate
    -0.69
     Subtle
    -0.68
    erest
    -0.67
    ":["
    -0.66
     Ninth
    -0.66
    target
    -0.65
    POSITIVE LOGITS
     Jr
    1.20
    uez
    0.88
     Sr
    0.88
    igne
    0.87
     heir
    0.85
    çīĪ
    0.84
    arcer
    0.84
    agna
    0.83
    abba
    0.80
    opez
    0.77
    Activations Density 0.005%

    No Known Activations