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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 12176
    Prev
    Next
    INDEX
    Explanations

    the letter 'T' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the letter "T"

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.84
    theless
    -0.80
     destro
    -0.74
     ment
    -0.72
    EStream
    -0.70
     cannabin
    -0.67
     actionGroup
    -0.66
    espie
    -0.63
     Senegal
    -0.63
    wagen
    -0.62
    POSITIVE LOGITS
    ribute
    1.29
    ARGET
    1.27
    olerance
    1.22
    ributes
    1.18
    uple
    1.17
    ractor
    1.16
    empt
    1.13
    ucked
    1.13
    asks
    1.12
    agged
    1.11
    Activations Density 0.049%

    No Known Activations