© 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. 1-RES-JB
    11. 20208
    Prev
    Next
    INDEX
    Explanations

    descriptions or discussions related to the perspective of a first-person shooter video game

    oai_token-act-pair · gpt-3.5-turbo

    references to first-person and third-person perspectives in the context of gaming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actionGroup
    -0.75
    FACE
    -0.67
    UFF
    -0.66
    enthal
    -0.63
    irc
    -0.62
    YN
    -0.61
    Tx
    -0.61
    ERO
    -0.60
    DL
    -0.60
    SB
    -0.59
    POSITIVE LOGITS
    person
    1.08
    nel
    1.02
    ngth
    0.91
    acters
    0.91
    hood
    0.91
    geant
    0.84
    utenant
    0.82
    ality
    0.82
    ority
    0.82
    uscript
    0.82
    Activations Density 0.008%

    No Known Activations