© 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. 9030
    Prev
    Next
    INDEX
    Explanations

    phrases related to the abbreviation "LA", most likely referring to Los Angeles

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or establishment called "La."

    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
    lessly
    -0.78
    Ö¼
    -0.78
     sidx
    -0.74
    manship
    -0.71
     AAP
    -0.70
    cffff
    -0.68
    ICLE
    -0.65
    addon
    -0.64
    swer
    -0.64
    66666666
    -0.63
    POSITIVE LOGITS
    vel
    1.16
    uren
    1.07
    TeX
    1.01
    very
    0.99
    ver
    0.96
    verty
    0.93
     Marse
    0.92
    quire
    0.92
    vern
    0.91
    Font
    0.86
    Activations Density 0.022%

    No Known Activations