© 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. 6524
    Prev
    Next
    INDEX
    Explanations

    recipes or cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    specific names and attributes within a context, such as food recipes or universities

    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
     Alger
    -0.82
     Dag
    -0.80
     Algeria
    -0.78
     Elf
    -0.78
     Takeru
    -0.76
    Els
    -0.76
     Yemeni
    -0.76
    alia
    -0.74
     Haku
    -0.74
     elves
    -0.73
    POSITIVE LOGITS
    p
    1.33
    P
    1.32
    PP
    1.30
    Ps
    1.27
    PI
    1.22
    PB
    1.19
     P
    1.18
    PE
    1.14
    PO
    1.14
    ps
    1.13
    Activations Density 0.781%

    No Known Activations