© 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. 4-RES-JB
    11. 11299
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific organization, likely related to news or politics

    oai_token-act-pair · gpt-3.5-turbo

    the mention of the group "Hamas."

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

    No Comments

    Negative Logits
    manship
    -0.89
    âķIJ
    -0.86
    */(
    -0.84
    eenth
    -0.83
    eers
    -0.82
    icipated
    -0.78
    ãĥ¼ãĥĨ
    -0.76
    ij士
    -0.76
    orative
    -0.75
    eering
    -0.74
    POSITIVE LOGITS
    Ha
    0.97
    vel
    0.96
    irst
    0.94
     Ha
    0.89
    ifa
    0.89
    iku
    0.88
    pless
    0.87
    iky
    0.84
    iley
    0.84
    aretz
    0.81
    Activations Density 0.006%

    No Known Activations