© 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. 0-RES-JB
    11. 1176
    Prev
    Next
    INDEX
    Explanations

    terms related to recruitment or hiring

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "recruiting" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ñ
    -0.86
    Í
    -0.83
    wx
    -0.71
    grain
    -0.71
     eas
    -0.70
    WB
    -0.69
     Objects
    -0.68
    Ô
    -0.67
     Peb
    -0.66
    upper
    -0.65
    POSITIVE LOGITS
     recruiting
    3.55
     recruit
    3.54
     recruitment
    3.05
     recru
    2.97
     recruits
    2.53
     recruited
    2.44
     hiring
    1.59
     enlist
    1.49
     hire
    1.37
     indoctr
    1.30
    Activations Density 0.035%

    No Known Activations