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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 23825
    Prev
    Next
    INDEX
    Explanations

    mentions of first-person perspective in video games

    oai_token-act-pair · gpt-3.5-turbo

    references to 'first-person' perspectives in video games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tro
    -0.83
    unctions
    -0.69
    tnc
    -0.67
    natureconservancy
    -0.67
    HOU
    -0.66
    Recomm
    -0.65
     Lann
    -0.63
    eeks
    -0.63
    xual
    -0.63
    enthal
    -0.62
    POSITIVE LOGITS
     pronouns
    0.80
     pronoun
    0.78
    owicz
    0.76
     experiences
    0.76
     shooter
    0.76
     shooters
    0.75
    atively
    0.74
    hood
    0.73
     plural
    0.73
    opter
    0.73
    Activations Density 0.031%

    No Known Activations