© 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. 4-RES-JB
    11. 14882
    Prev
    Next
    INDEX
    Explanations

    mentions of corporate entities or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to corporations and the influence of big business in politics

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

    No Comments

    Negative Logits
    ydia
    -0.88
     [|
    -0.77
    ĺħ
    -0.73
    ttp
    -0.73
    umbnail
    -0.71
    tml
    -0.70
    ++++++++
    -0.68
    ;;;;;;;;;;;;
    -0.67
    cific
    -0.66
     Anniversary
    -0.65
    POSITIVE LOGITS
     lobbyists
    1.02
     mogul
    1.00
     mog
    0.89
     lobbyist
    0.84
     executives
    0.82
     industries
    0.82
     CEOs
    0.81
     headquartered
    0.80
     firms
    0.79
     insurers
    0.78
    Activations Density 0.202%

    No Known Activations