© 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. 9-RES-JB
    11. 1592
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the intensity or nature of a quality or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "such a" or "such an" followed by an adjective or description

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ntil
    -0.90
    iliation
    -0.77
    iliate
    -0.73
    achev
    -0.70
    eanor
    -0.69
     Murd
    -0.67
    doctor
    -0.67
    kson
    -0.66
    achus
    -0.66
    idel
    -0.66
    POSITIVE LOGITS
     marvelous
    0.77
     magnificent
    0.77
     wonderful
    0.76
     proportions
    0.75
     phenomenal
    0.75
     mundane
    0.75
     amazing
    0.75
     splendid
    0.73
     blatant
    0.73
     incredible
    0.73
    Activations Density 0.045%

    No Known Activations