© 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. 10-RES-JB
    11. 6612
    Prev
    Next
    INDEX
    Explanations

    mentions of consulting services

    oai_token-act-pair · gpt-3.5-turbo

    terms related to consulting services and firms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nings
    -0.77
    velt
    -0.69
    utter
    -0.68
    buck
    -0.68
    lings
    -0.67
    enes
    -0.66
    runners
    -0.65
     celebrations
    -0.64
     Haram
    -0.63
    emp
    -0.62
    POSITIVE LOGITS
     firm
    0.99
     firms
    0.95
     advising
    0.92
     consultancy
    0.88
     services
    0.85
     advise
    0.84
     consulting
    0.82
    ancies
    0.81
     clients
    0.80
     consultants
    0.80
    Activations Density 0.056%

    No Known Activations