© 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. 1-RES-JB
    11. 3689
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "later" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to events or information that occurred after an initial mention

    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
    Feel
    -0.71
    Know
    -0.67
    eye
    -0.67
    ãĤ±
    -0.67
    EO
    -0.66
    cking
    -0.65
    rod
    -0.65
    HY
    -0.64
     Haram
    -0.64
    Ped
    -0.64
    POSITIVE LOGITS
    theless
    0.85
     later
    0.82
     iterations
    0.81
    osta
    0.80
    etheless
    0.80
     satell
    0.79
     destro
    0.76
    noon
    0.76
    aneously
    0.74
     generations
    0.74
    Activations Density 0.029%

    No Known Activations