Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 12150
    Prev
    Next
    INDEX
    Explanations

    personal pronouns combined with verbs indicating physical presence or action towards others

    oai_token-act-pair · gpt-3.5-turbo

    references to interactions and perceptions involving individuals

    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
    elsen
    -0.76
    ģĸ
    -0.64
    aceutical
    -0.61
    livion
    -0.60
    creation
    -0.60
    isma
    -0.60
    oso
    -0.60
     revelations
    -0.59
    onite
    -0.57
     notion
    -0.56
    POSITIVE LOGITS
     alive
    0.97
     smiling
    0.89
     behaving
    0.83
     grinning
    0.82
     sitting
    0.78
     interacting
    0.78
     unfold
    0.76
     cruising
    0.74
     lurking
    0.74
     naked
    0.74
    Activations Density 0.157%

    No Known Activations