© 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. 7459
    Prev
    Next
    INDEX
    Explanations

    details related to recruiting processes for employees, including requirements and instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to hiring and recruitment processes

    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
    violence
    -0.89
     Glac
    -0.79
    lag
    -0.77
    acas
    -0.73
     looting
    -0.71
    itsch
    -0.69
    wart
    -0.69
    peace
    -0.69
    Battery
    -0.69
     peacefully
    -0.68
    POSITIVE LOGITS
     applicants
    1.80
     recru
    1.64
     applicant
    1.55
     hiring
    1.49
     audition
    1.49
     vacancies
    1.46
     recruitment
    1.40
     recruit
    1.39
    Applic
    1.38
     candidates
    1.35
    Activations Density 0.651%

    No Known Activations