© 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. 20187
    Prev
    Next
    INDEX
    Explanations

    phrases related to business partnerships

    oai_token-act-pair · gpt-3.5-turbo

    references to partnerships or collaborative relationships

    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
     Sabha
    -0.81
    Naz
    -0.79
    aston
    -0.73
    ouses
    -0.73
    SpaceEngineers
    -0.67
    rise
    -0.67
    AE
    -0.65
    uther
    -0.65
    anism
    -0.64
    asty
    -0.63
    POSITIVE LOGITS
     partners
    1.32
     partner
    1.26
     collaborators
    0.95
     Partner
    0.92
    hips
    0.85
     collaborator
    0.82
    itute
    0.77
     colleagues
    0.73
     partnered
    0.72
     contracted
    0.71
    Activations Density 0.011%

    No Known Activations