© 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. 4933
    Prev
    Next
    INDEX
    Explanations

    personal pronouns combined with verbs related to movement

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and phrases indicating movement or presence in various locations

    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
    livious
    -0.67
     Rasmussen
    -0.63
     expectations
    -0.62
     Debor
    -0.62
    omas
    -0.61
     NAACP
    -0.61
    liest
    -0.58
     Alternative
    -0.57
     Accounting
    -0.57
    ALLY
    -0.57
    POSITIVE LOGITS
     touched
    0.96
     slightest
    0.96
    soever
    0.95
    ever
    0.80
     imaginable
    0.80
     encount
    0.78
    charge
    0.77
    iod
    0.76
     touch
    0.75
     encountered
    0.75
    Activations Density 0.171%

    No Known Activations