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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 23025
    Prev
    Next
    INDEX
    Explanations

    names with the string "m" followed by a digit from 9 to 10

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'm'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.69
     pitch
    -0.66
     begg
    -0.62
     tipped
    -0.62
     foul
    -0.60
     ramps
    -0.60
     Pengu
    -0.59
    */(
    -0.59
    irtual
    -0.58
    POSITIVE LOGITS
    otor
    1.23
    ichael
    1.21
    asonic
    1.20
    ormon
    1.19
    asonry
    1.17
    obil
    1.16
    obiles
    1.15
    useum
    1.14
    ortal
    1.11
    uppet
    1.08
    Activations Density 0.055%

    No Known Activations