© 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. 13025
    Prev
    Next
    INDEX
    Explanations

    dates and times posted along with related content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Posted" followed by a timestamp

    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
    atern
    -0.85
    ugal
    -0.82
    fell
    -0.80
    asters
    -0.75
    obs
    -0.71
    apers
    -0.70
    aternity
    -0.68
    asts
    -0.66
    oped
    -0.65
    appers
    -0.65
    POSITIVE LOGITS
    Posted
    1.31
     Thumbnails
    0.80
    Reviewed
    0.79
     Posted
    0.76
    erick
    0.74
    Edit
    0.73
     Comments
    0.71
    ertodd
    0.70
    Updated
    0.69
     Username
    0.69
    Activations Density 0.006%

    No Known Activations