© 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. 9-RES-JB
    11. 18177
    Prev
    Next
    INDEX
    Explanations

    mentioning of various public services such as education, healthcare, housing, and employment

    oai_token-act-pair · gpt-3.5-turbo

    references to social services and equal access to resources

    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
    igible
    -0.74
     Conspiracy
    -0.72
     Cthulhu
    -0.72
    inous
    -0.71
    scrib
    -0.71
    umn
    -0.67
    igmatic
    -0.67
    icol
    -0.66
    ón
    -0.65
     Merlin
    -0.64
    POSITIVE LOGITS
     sanitation
    1.28
     healthcare
    1.21
     literacy
    1.15
     hygiene
    1.13
     pensions
    1.12
     welfare
    1.10
     education
    1.08
     nutrition
    1.06
     housing
    1.06
     medicines
    1.06
    Activations Density 0.281%

    No Known Activations