© 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. 10-RES-JB
    6. 12168
    Prev
    Next
    INDEX
    Explanations

    consecutive repeated words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific people or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cah
    -1.12
     CAM
    -1.05
    CM
    -0.99
     Cay
    -0.98
    Charl
    -0.96
     Cam
    -0.94
     Cot
    -0.93
     Charlotte
    -0.92
     Cth
    -0.92
     Cly
    -0.92
    POSITIVE LOGITS
     Tycoon
    0.89
    unk
    0.88
    unks
    0.81
    çĶŁ
    0.79
    Hero
    0.78
    oom
    0.77
     Levin
    0.75
    ondo
    0.74
    inion
    0.74
    ink
    0.74
    Activations Density 0.360%

    No Known Activations