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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18582
    Prev
    Next
    INDEX
    Explanations

    keywords or phrases related to entire entities or systems

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ent" and its variations, indicating a focus on words related to entities or entities themselves

    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
    士
    -0.81
     Spears
    -0.73
     hearts
    -0.72
     tiss
    -0.68
    manship
    -0.65
     CPC
    -0.65
     tremend
    -0.64
    BuyableInstoreAndOnline
    -0.63
    phrine
    -0.63
     sterling
    -0.61
    POSITIVE LOGITS
    ropy
    1.61
    rance
    1.29
    reprene
    1.23
    raction
    1.18
    ertain
    1.17
    ire
    1.14
    itled
    1.11
    rants
    1.09
    itle
    1.03
    ribute
    1.03
    Activations Density 0.036%

    No Known Activations