© 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. 11-RES-JB
    11. 22510
    Prev
    Next
    INDEX
    Explanations

    instances of meetings and interactions between individuals in positions of power or influence

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to meetings or discussions between individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aan
    -0.81
     slur
    -0.80
    void
    -0.77
    é¾įå
    -0.76
    ffff
    -0.72
    é¾įåĸļ士
    -0.71
     "$:/
    -0.70
    rary
    -0.68
    ©¶æ¥µ
    -0.68
    ny
    -0.68
    POSITIVE LOGITS
     representatives
    1.41
     mayors
    1.25
     governors
    1.24
     CEOs
    1.22
     chiefs
    1.19
     counterparts
    1.16
     ambassadors
    1.16
     stakeholders
    1.13
     leaders
    1.13
     secretaries
    1.10
    Activations Density 0.278%

    No Known Activations