© 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. 1-RES-JB
    11. 23358
    Prev
    Next
    INDEX
    Explanations

    names or references to individuals named "Jalen" or variations thereof

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or entities, particularly those associated with a cartel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parenthood
    -0.82
     Nationwide
    -0.78
     Dying
    -0.68
     SUP
    -0.68
    天
    -0.67
     Millennium
    -0.66
    ãĥĩãĤ£
    -0.66
     Debor
    -0.65
     Brave
    -0.64
    ãģį
    -0.64
    POSITIVE LOGITS
     Jal
    1.18
    amel
    1.02
    aya
    0.89
    aji
    0.87
    interstitial
    0.87
    ules
    0.85
    olla
    0.85
    ppo
    0.85
    ouri
    0.84
    peg
    0.83
    Activations Density 0.004%

    No Known Activations