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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 12136
    Prev
    Next
    INDEX
    Explanations

    phrases where the letter 'T' is followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'T' in various contexts

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.94
    EStream
    -0.85
     actionGroup
    -0.81
    76561
    -0.80
    espie
    -0.72
    ãĤ¡
    -0.69
    vernment
    -0.68
     Senegal
    -0.66
    ħĭ
    -0.66
     Appalach
    -0.65
    POSITIVE LOGITS
    ribute
    1.25
    ARGET
    1.17
    ributes
    1.12
    asks
    1.12
    olerance
    1.10
    rench
    1.10
    ractor
    1.08
    ribune
    1.08
    ween
    1.06
    agged
    1.06
    Activations Density 0.034%

    No Known Activations