© 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. 12524
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events providing different perspectives

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Dep" or its variations, suggesting a focus on government or organizational references

    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
     Pose
    -0.96
    enegger
    -0.84
    FORE
    -0.83
    çĦ
    -0.81
     Hole
    -0.80
    MER
    -0.75
    nings
    -0.73
     deaf
    -0.73
    çķ
    -0.71
    glers
    -0.71
    POSITIVE LOGITS
    recated
    1.31
    uties
    1.24
    uty
    1.21
    ository
    1.17
    artments
    1.16
    ravity
    1.12
    osit
    1.12
    artment
    1.11
    orters
    1.10
    raved
    1.09
    Activations Density 0.017%

    No Known Activations