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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 4242
    Prev
    Next
    INDEX
    Explanations

    versions and updates of software

    oai_token-act-pair · gpt-3.5-turbo

    version numbers and numeric identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     affili
    -0.75
     clos
    -0.71
     ris
    -0.66
     frivolous
    -0.66
     jugg
    -0.66
     habit
    -0.66
     waged
    -0.65
     dared
    -0.64
     proposition
    -0.64
     closer
    -0.64
    POSITIVE LOGITS
    0
    1.45
    1
    1.32
    jar
    1.29
    tar
    1.27
    7601
    1.24
    gz
    1.23
    2
    1.23
    3
    1.22
    840
    1.20
    201
    1.18
    Activations Density 0.036%

    No Known Activations