© 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. 23465
    Prev
    Next
    INDEX
    Explanations

    architectural elements and descriptions in a text

    oai_token-act-pair · gpt-3.5-turbo

    features related to physical structures and their components

    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
    Lear
    -0.72
    puting
    -0.69
    necessary
    -0.67
    hemy
    -0.64
     Niet
    -0.64
     Wrong
    -0.63
    expected
    -0.63
    zynski
    -0.63
    Reporting
    -0.63
    PDATE
    -0.63
    POSITIVE LOGITS
     consists
    1.45
     resembles
    1.34
     contains
    1.33
     comprises
    1.27
     protr
    1.24
     sits
    1.22
     depicts
    1.18
     incorporates
    1.17
     consist
    1.17
     boasts
    1.14
    Activations Density 0.305%

    No Known Activations