© 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. 10-RES-JB
    11. 10527
    Prev
    Next
    INDEX
    Explanations

    phrases containing the abbreviation "SP" followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "SP" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     behold
    -0.65
    naires
    -0.64
    ãĥĥ
    -0.62
    hoe
    -0.61
    forced
    -0.61
    tons
    -0.60
    âĶģ
    -0.60
     Commodore
    -0.59
     subord
    -0.59
    stretched
    -0.59
    POSITIVE LOGITS
    EED
    1.46
    OIL
    1.35
    ORTS
    1.29
    ORT
    1.18
    ECT
    1.12
    ONSORED
    1.11
    ACE
    1.05
    LC
    0.99
    ERSON
    0.97
    IRE
    0.97
    Activations Density 0.023%

    No Known Activations