© 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. 1009
    Prev
    Next
    INDEX
    Explanations

    impacts on various sectors and entities due to external factors or events

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to the impact of policies and environmental factors on food and civil liberties

    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
     Clown
    -0.66
    BuyableInstoreAndOnline
    -0.66
     alphabet
    -0.62
     preceded
    -0.61
     replaced
    -0.59
     Bastard
    -0.59
     supers
    -0.58
     esche
    -0.57
     Bild
    -0.57
     absent
    -0.57
    POSITIVE LOGITS
     morale
    1.03
     livelihood
    0.90
     downstream
    0.86
     ecosystems
    0.86
     psyche
    0.83
     fragile
    0.82
     industries
    0.82
     perceptions
    0.82
     economies
    0.82
     populations
    0.81
    Activations Density 0.550%

    No Known Activations