© 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. 8-RES-JB
    11. 22538
    Prev
    Next
    INDEX
    Explanations

    personal pronouns referring to the speaker, specifically 'I'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "I"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alternative
    -0.64
    eworthy
    -0.63
     mutants
    -0.61
     Uriel
    -0.60
     uniforms
    -0.59
     Rolls
    -0.58
     Consortium
    -0.57
     Gale
    -0.56
     Bottom
    -0.54
     Sidney
    -0.54
    POSITIVE LOGITS
    'm
    1.70
     am
    1.26
    've
    1.25
     myself
    1.04
     suppose
    1.00
    'd
    1.00
    RL
    1.00
    verson
    0.97
    ggy
    0.97
    zzo
    0.94
    Activations Density 0.244%

    No Known Activations