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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 22509
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific time or location events

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Around" followed by numerical details or time references

    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
    venge
    -0.74
     tatt
    -0.67
    imm
    -0.67
     duct
    -0.66
     istg
    -0.64
     gard
    -0.61
    qua
    -0.60
     harb
    -0.59
    straight
    -0.59
    TF
    -0.59
    POSITIVE LOGITS
     Around
    0.85
    lihood
    0.85
    atform
    0.82
    abouts
    0.77
    iversal
    0.75
     Them
    0.71
    ength
    0.71
    £ı
    0.71
    Around
    0.71
    pread
    0.70
    Activations Density 0.013%

    No Known Activations