Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 4394
    Prev
    Next
    INDEX
    Explanations

    phrases related to professions, job prospects, and economic opportunities

    oai_token-act-pair · gpt-3.5-turbo

    statements about job opportunities and expectations related to education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PCB
    -0.79
     Atmosp
    -0.74
     Mole
    -0.74
     scrut
    -0.74
    canon
    -0.72
    RFC
    -0.71
     edits
    -0.71
     Tracks
    -0.69
     Shooting
    -0.68
    Gallery
    -0.67
    POSITIVE LOGITS
     vocational
    1.21
     affluent
    1.20
     subsidized
    1.16
     graduates
    1.10
     wealthier
    1.09
     incomes
    1.08
     salaries
    1.05
     lucrative
    1.05
     disproportionately
    1.03
    paying
    1.03
    Activations Density 0.947%

    No Known Activations