© 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. 2542
    Prev
    Next
    INDEX
    Explanations

    phrases related to various business models

    oai_token-act-pair · gpt-3.5-turbo

    references to business models and practices

    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
    ãĥŃ
    -0.67
    hus
    -0.67
     EW
    -0.66
    ifer
    -0.66
     LW
    -0.65
    gger
    -0.64
    ados
    -0.63
    apego
    -0.63
    arity
    -0.63
    ople
    -0.60
    POSITIVE LOGITS
     dealings
    1.10
     ventures
    1.07
    INESS
    1.03
     enterprises
    0.97
    woman
    0.97
     owners
    0.94
     venture
    0.92
    people
    0.91
     model
    0.91
    Entity
    0.89
    Activations Density 0.057%

    No Known Activations