© 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. 19330
    Prev
    Next
    INDEX
    Explanations

    hyphenated adjectives describing something as "high-?" with a following descriptive term

    oai_token-act-pair · gpt-3.5-turbo

    terms related to high-profile or high-ranking entities and contextual 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
     Creator
    -0.79
    ĸļ
    -0.72
     Dunham
    -0.72
     Borders
    -0.71
     Gum
    -0.70
     Dull
    -0.70
    issors
    -0.69
     Doomsday
    -0.69
     Schumer
    -0.69
    ulhu
    -0.69
    POSITIVE LOGITS
    level
    1.33
    powered
    1.27
    ranking
    1.21
    priced
    1.17
    sized
    1.16
    sounding
    1.14
    quality
    1.13
    grade
    1.13
    enough
    1.13
    profile
    1.12
    Activations Density 0.061%

    No Known Activations