© 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. 10-RES-JB
    11. 17258
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to individuals in conversational 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
    20439
    -0.79
     Parables
    -0.78
     Consortium
    -0.76
     è£ıè
    -0.70
    ĵĺ
    -0.68
    ãĤ¤ãĥĪ
    -0.68
    igmatic
    -0.67
     Enhance
    -0.65
    ãĤ´ãĥ³
    -0.65
    Indeed
    -0.64
    POSITIVE LOGITS
     got
    1.35
     didn
    1.35
     went
    1.33
     didnt
    1.32
     stayed
    1.27
     threw
    1.27
     blew
    1.25
     messed
    1.23
     forgot
    1.22
     kept
    1.21
    Activations Density 0.330%

    No Known Activations