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

    Neuronpedia

    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. 7593
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal thoughts or narration

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal identity and status

    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
     accompanies
    -0.74
     bearer
    -0.72
    bda
    -0.70
     IMAGES
    -0.68
     narration
    -0.67
     autop
    -0.64
    edly
    -0.63
     cryptoc
    -0.63
     charism
    -0.61
     thumbnail
    -0.60
    POSITIVE LOGITS
     gonna
    1.02
    [/
    0.89
    âĢ
    0.87
    !!"
    0.81
    Pak
    0.81
    ""
    0.78
     fuckin
    0.75
    !'
    0.74
    """
    0.74
    »
    0.71
    Activations Density 0.137%

    No Known Activations