© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14743
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal accomplishment or recognition

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to making a name for oneself

    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
     Bowser
    -0.70
     NCT
    -0.57
     Edwards
    -0.56
     DOE
    -0.55
     Anon
    -0.54
     rapper
    -0.53
     Engineers
    -0.53
     Kw
    -0.53
    """
    -0.52
     Tiff
    -0.52
    POSITIVE LOGITS
    ãĥ¼ãĥĨãĤ£
    0.86
    ufact
    0.85
    ewitness
    0.84
    izontal
    0.81
    vironment
    0.80
    aughtered
    0.80
    ibly
    0.79
    ibles
    0.79
    urally
    0.78
    oaded
    0.78
    Activations Density 1.237%

    No Known Activations