© 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. 13143
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by a past-tense verb

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in a conversational or reported speech context

    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
     Dominion
    -0.71
    piring
    -0.61
     Entry
    -0.60
    icle
    -0.59
     Vine
    -0.59
    Fail
    -0.58
     Mandatory
    -0.57
     Dirty
    -0.56
    Row
    -0.54
     Resistance
    -0.54
    POSITIVE LOGITS
     regretted
    1.16
    'd
    1.15
     consulted
    1.08
     encount
    1.05
     hoped
    1.04
     expects
    1.03
     personally
    1.01
     believes
    0.97
     understands
    0.95
     empath
    0.95
    Activations Density 0.115%

    No Known Activations