© 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. 11-RES-JB
    11. 20217
    Prev
    Next
    INDEX
    Explanations

    mentions of different industry sectors and job growth or losses in those sectors

    oai_token-act-pair · gpt-3.5-turbo

    references to various economic sectors and industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rious
    -0.68
    Jes
    -0.68
    oleon
    -0.66
    æĢ
    -0.66
     Stories
    -0.64
     Deity
    -0.64
    olerance
    -0.64
    Attempts
    -0.64
    unity
    -0.63
     Shame
    -0.63
    POSITIVE LOGITS
     agriculture
    1.38
     forestry
    1.36
     telecommunications
    1.31
     aerospace
    1.31
     manufacturing
    1.26
     pharmaceutical
    1.24
     textile
    1.22
     automotive
    1.22
     semic
    1.15
     telecom
    1.15
    Activations Density 0.370%

    No Known Activations