© 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. 10-RES-JB
    11. 4789
    Prev
    Next
    INDEX
    Explanations

    time-related references, particularly indicating a sequence or duration

    oai_token-act-pair · gpt-3.5-turbo
    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
    quartered
    -0.69
     suppose
    -0.63
    glass
    -0.59
    ciplinary
    -0.59
    sama
    -0.59
    CD
    -0.58
    arget
    -0.58
    igans
    -0.57
    grown
    -0.57
    ICE
    -0.56
    POSITIVE LOGITS
     entirety
    1.68
     remainder
    1.60
     entire
    1.48
     foreseeable
    1.39
     majority
    1.37
     rest
    1.35
     next
    1.26
     duration
    1.21
     longest
    1.21
     whole
    1.18
    Activations Density 0.101%

    No Known Activations