© 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. 11-RES-JB
    11. 10161
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to specific people and their actions

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, emphasizing their actions and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.76
    ĵĺ
    -0.73
    etheless
    -0.65
    include
    -0.64
    actionDate
    -0.62
     Parables
    -0.61
    HOW
    -0.60
     è£ıè
    -0.60
     §§
    -0.60
     Shutterstock
    -0.59
    POSITIVE LOGITS
     knows
    1.20
     wants
    1.19
     loves
    1.17
     understands
    1.16
    zbollah
    1.13
     hasn
    1.12
    'll
    1.12
     doesn
    1.11
    's
    1.09
     thinks
    1.08
    Activations Density 0.163%

    No Known Activations