© 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. 9-RES-JB
    11. 13767
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names related to various entities

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "ass" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISA
    -0.71
     bite
    -0.66
     bye
    -0.65
    Gi
    -0.65
    tc
    -0.65
    ãĤ¡
    -0.64
    MSN
    -0.64
    fare
    -0.61
    ãĤ§
    -0.61
    BY
    -0.60
    POSITIVE LOGITS
    assin
    1.49
    ociation
    1.31
    oci
    1.29
    istant
    1.29
    ociate
    1.24
    essment
    1.14
    istance
    1.13
    ortment
    1.13
    achusetts
    1.11
    essor
    1.11
    Activations Density 0.031%

    No Known Activations