© 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. 4-RES-JB
    11. 2464
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names within dialogues

    oai_token-act-pair · gpt-3.5-turbo

    instances of dialogue and conversation formatting

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

    No Comments

    Negative Logits
     centrally
    -0.76
     este
    -0.68
     valued
    -0.67
     honoured
    -0.64
     estranged
    -0.64
     hitherto
    -0.64
     administr
    -0.64
     individually
    -0.64
     quaint
    -0.63
     encomp
    -0.63
    POSITIVE LOGITS
    Anyway
    0.99
    Narr
    0.94
    laughs
    0.94
    ITNESS
    0.91
    Reply
    0.90
    Laughs
    0.87
    Interview
    0.87
    Coach
    0.86
    -----------
    0.85
    --------------------------------------------------------
    0.85
    Activations Density 0.402%

    No Known Activations