© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 3056
    Prev
    Next
    INDEX
    Explanations

    instances where something has already been done or is in place

    oai_token-act-pair · gpt-3.5-turbo

    the word "already" and its context in relation to ongoing or past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rent
    -0.89
    second
    -0.75
    case
    -0.74
    also
    -0.74
    anches
    -0.74
    udge
    -0.72
    sim
    -0.68
    catentry
    -0.68
    rus
    -0.67
    bart
    -0.67
    POSITIVE LOGITS
     underway
    0.88
     begun
    0.83
     surpassed
    0.81
     established
    0.79
     existed
    0.79
     knew
    0.79
     accounted
    0.78
     booked
    0.77
     acquainted
    0.75
     racked
    0.73
    Activations Density 0.055%

    No Known Activations