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

    Neuronpedia

    Jacobian LensNEW
    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. 1514
    Prev
    Next
    INDEX
    Explanations

    keywords related to the abbreviation "SP" used in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the abbreviation "SP" followed by a number

    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
    ãĥĥãĥĪ
    -0.86
    sbm
    -0.78
    gerald
    -0.71
    izabeth
    -0.70
    algia
    -0.69
    hower
    -0.68
    FactoryReloaded
    -0.68
    ablishment
    -0.67
    hof
    -0.66
    âĶģ
    -0.66
    POSITIVE LOGITS
    EED
    1.37
    OIL
    1.12
    ORT
    1.05
    ONSORED
    1.03
    IR
    1.01
    ARK
    0.96
    IDER
    0.94
    ORTS
    0.92
    iral
    0.91
    ECT
    0.91
    Activations Density 0.008%

    No Known Activations