© 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. 8-RES-JB
    11. 4086
    Prev
    Next
    INDEX
    Explanations

    words related to state-controlled or state-owned entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to state-owned or government-run entities and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alos
    -0.84
    bra
    -0.80
    asso
    -0.80
    osponsors
    -0.79
    oother
    -0.76
    eeks
    -0.75
    rehend
    -0.75
    LOD
    -0.74
    thia
    -0.74
    irlf
    -0.73
    POSITIVE LOGITS
     enterprises
    1.23
     enterprise
    0.98
     entity
    0.95
     corporation
    0.95
     monopoly
    0.94
     entities
    0.91
     institutions
    0.91
     businesses
    0.89
     corporations
    0.89
     Enterprises
    0.85
    Activations Density 0.053%

    No Known Activations