© 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. 6-RES-JB
    11. 7988
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions or steps taken in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters indicating significance or emphasis in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bunny
    -0.81
     Somerset
    -0.71
     Manhattan
    -0.67
    çĶ°
    -0.66
     Vera
    -0.65
     Roc
    -0.64
     Yon
    -0.62
     reception
    -0.62
    ctors
    -0.61
     Glou
    -0.60
    POSITIVE LOGITS
    âĹ¼
    0.97
    âĢł
    0.91
    0.91
    ¯
    0.89
    ¬
    0.86
    §
    0.86
    0.83
    uph
    0.82
    ¹
    0.79
    į
    0.78
    Activations Density 0.282%

    No Known Activations