© 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. 2790
    Prev
    Next
    INDEX
    Explanations

    positive descriptions or achievements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant moments or changes in context

    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
    roup
    -0.61
    lihood
    -0.59
    intensive
    -0.58
     Archdemon
    -0.54
    icipated
    -0.54
     Lent
    -0.53
     Anonymous
    -0.52
    abled
    -0.52
    mol
    -0.52
     Fires
    -0.51
    POSITIVE LOGITS
     exception
    1.01
     Exhibit
    1.00
     exempl
    0.91
    empl
    0.86
     accordingly
    0.86
     remedy
    0.84
     example
    0.82
     illustrate
    0.81
     proof
    0.81
     illust
    0.80
    Activations Density 0.542%

    No Known Activations