© 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. 8-RES-JB
    11. 15058
    Prev
    Next
    INDEX
    Explanations

    phrases related to the direction or manner in which something is done

    oai_token-act-pair · gpt-3.5-turbo

    phrases that imply opposition or contrast, often using the term "the other way" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rac
    -0.59
    obyl
    -0.56
     Invalid
    -0.55
    iaz
    -0.53
    aternal
    -0.52
    ropy
    -0.51
    operated
    -0.51
    ract
    -0.51
    ihu
    -0.51
    ihar
    -0.51
    POSITIVE LOGITS
    heet
    0.66
    Course
    0.61
     opio
    0.59
    ogly
    0.58
    ament
    0.58
     nowhere
    0.58
    strate
    0.55
     roundup
    0.54
    button
    0.54
    tile
    0.54
    Activations Density 0.663%

    No Known Activations