© 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. 8-RES-JB
    11. 969
    Prev
    Next
    INDEX
    Explanations

    words related to geopolitical situations and military operations

    oai_token-act-pair · gpt-3.5-turbo

    important statements related to military operations and international relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abus
    -0.74
    OTO
    -0.71
    Buzz
    -0.69
    }.
    -0.65
     PLEASE
    -0.65
    arat
    -0.64
    @@
    -0.63
     deserve
    -0.62
    ico
    -0.61
    worthiness
    -0.60
    POSITIVE LOGITS
     predomin
    0.70
     indistinguishable
    0.68
    natureconservancy
    0.67
    ãĥĩãĤ£
    0.67
    ided
    0.67
    stood
    0.66
     pitted
    0.63
    emin
    0.61
     distinction
    0.61
    uchs
    0.60
    Activations Density 0.541%

    No Known Activations