© 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. 16322
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Pas"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or community, particularly "Pasadena"

    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
    */(
    -0.79
    è¦ļéĨĴ
    -0.74
    ACTED
    -0.70
    adder
    -0.69
    é¾
    -0.67
    acts
    -0.66
    ship
    -0.65
    ocating
    -0.64
    sheet
    -0.61
    orph
    -0.60
    POSITIVE LOGITS
     Pas
    1.17
    chal
    1.13
    sth
    1.08
    nown
    1.03
    apon
    0.97
    ques
    0.91
    quet
    0.86
    adena
    0.83
     pas
    0.83
    daq
    0.81
    Activations Density 0.006%

    No Known Activations