© 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. 2-RES-JB
    11. 23982
    Prev
    Next
    INDEX
    Explanations

    instances where the word "probably" is used

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "probably" indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issy
    -0.83
    gencies
    -0.78
    lette
    -0.74
    eller
    -0.72
    elight
    -0.72
    lain
    -0.71
    uality
    -0.71
    yer
    -0.71
    leground
    -0.70
    ritch
    -0.70
    POSITIVE LOGITS
     incent
    0.82
    Ń·
    0.75
    ©¶æ
    0.74
     ali
    0.74
     infer
    0.74
     assume
    0.73
     gonna
    0.72
     preferring
    0.71
     misunder
    0.70
     occas
    0.67
    Activations Density 0.017%

    No Known Activations