© 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. 22310
    Prev
    Next
    INDEX
    Explanations

    terms related to recruitment or enlisting

    oai_token-act-pair · gpt-3.5-turbo

    references to recruitment processes and related terms

    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
    Rated
    -0.75
    plain
    -0.70
     marvel
    -0.65
     Rockies
    -0.64
     Blessed
    -0.64
    vd
    -0.63
     touched
    -0.63
     blessed
    -0.63
    ashed
    -0.63
    owed
    -0.61
    POSITIVE LOGITS
     recruitment
    3.59
     recruiting
    1.50
     procurement
    1.30
     recru
    1.25
     mobilization
    1.24
     recruit
    1.23
     initiation
    1.20
     hiring
    1.15
     attrition
    1.15
     resettlement
    1.13
    Activations Density 0.024%

    No Known Activations