© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 20353
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly organization names and entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names of organizations or entities

    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
    riages
    -0.93
    codes
    -0.88
    efficients
    -0.85
    bats
    -0.85
    abases
    -0.81
    ities
    -0.81
    names
    -0.80
    units
    -0.79
    ernels
    -0.79
    pees
    -0.79
    POSITIVE LOGITS
     staffer
    1.14
     employee
    1.08
     spokeswoman
    1.07
     spokesperson
    1.06
     representative
    1.03
     colleague
    1.02
     spokesman
    0.98
     member
    0.94
     sticker
    0.94
     supporter
    0.92
    Activations Density 0.315%

    No Known Activations