© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 7933
    Prev
    Next
    INDEX
    Explanations

    phrases related to war and conflict

    oai_token-act-pair · gpt-3.5-turbo

    references to "War" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essee
    -0.99
    ħĭ
    -0.89
    sembly
    -0.83
    Ħ¢
    -0.82
    aminer
    -0.79
    issance
    -0.77
    İĭ
    -0.73
     suspic
    -0.71
    etsk
    -0.71
    OGR
    -0.69
    POSITIVE LOGITS
    rior
    1.43
    fare
    1.36
    riors
    1.36
    lords
    1.21
    locks
    1.20
    lord
    1.17
    ped
    1.06
    lock
    1.01
    horse
    1.00
    ring
    0.98
    Activations Density 0.028%

    No Known Activations