© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 20269
    Prev
    Next
    INDEX
    Explanations

    phrases related to the University of Kent

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character sequence "âĢ", which seems to be a formatting or encoding artifact

    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
     Glou
    -0.68
    çͰ
    -0.68
     guiActiveUnfocused
    -0.66
     scattering
    -0.64
     record
    -0.63
    ãĥ¼ãĥĨ
    -0.62
     Franch
    -0.62
     Records
    -0.59
     fib
    -0.59
     Tsuk
    -0.59
    POSITIVE LOGITS
    į
    0.85
    ¬
    0.84
    Ĵ
    0.84
    ¹
    0.84
    drivers
    0.81
    £
    0.80
    Ĭ
    0.79
    atures
    0.78
    moderate
    0.78
    catentry
    0.77
    Activations Density 0.400%

    No Known Activations