© 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. 7673
    Prev
    Next
    INDEX
    Explanations

    words related to the location "Palomar"

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and individuals connected to the name "Pal."

    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
    Ö¼
    -0.65
    OTOS
    -0.63
    gerald
    -0.59
    REDACTED
    -0.58
    :{
    -0.54
     Craw
    -0.54
    usercontent
    -0.53
     hurd
    -0.53
    glers
    -0.52
    EMENT
    -0.52
    POSITIVE LOGITS
    ieri
    0.87
    ophon
    0.79
    encia
    0.78
    ophone
    0.75
    nick
    0.70
     Nieto
    0.70
    ossom
    0.68
    steen
    0.68
    ocene
    0.67
    ength
    0.66
    Activations Density 0.121%

    No Known Activations