© 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. 10-RES-JB
    11. 24072
    Prev
    Next
    INDEX
    Explanations

    rankings or ratings

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to rankings and performance metrics

    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
    fol
    -0.67
     attendant
    -0.64
    unity
    -0.63
    erc
    -0.62
    embed
    -0.61
    emade
    -0.58
    iversary
    -0.58
    ERC
    -0.56
    emort
    -0.56
     playbook
    -0.56
    POSITIVE LOGITS
     seventh
    1.27
     sixth
    1.26
     ninth
    1.26
     eighth
    1.21
     fifth
    1.21
     fourth
    1.20
     second
    1.14
    second
    1.07
     tenth
    1.07
     lowly
    1.05
    Activations Density 0.111%

    No Known Activations