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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 13101
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names preceded by a single capital letter "T"

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific token representing the end of text or line

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
     ment
    -0.66
     diapers
    -0.66
     cannabin
    -0.63
     visuals
    -0.60
    TPPStreamerBot
    -0.59
     Arctic
    -0.59
     Atmosp
    -0.59
     Witcher
    -0.59
     destro
    -0.59
    POSITIVE LOGITS
    ARGET
    1.41
    ractor
    1.20
    ract
    1.17
    ravis
    1.16
    ribute
    1.13
    ottenham
    1.13
    EMP
    1.13
    empt
    1.13
    ruly
    1.13
    eddy
    1.10
    Activations Density 0.040%

    No Known Activations