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. 7-RES-JB
    6. 17547
    Prev
    Next
    INDEX
    Explanations

    the word "different" followed by various contexts or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "different" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ³³³³³³³³³³³³³³³³
    -0.79
    Never
    -0.74
     âĨij
    -0.70
    WARD
    -0.68
    âĢł
    -0.68
    Behind
    -0.62
    never
    -0.61
    QU
    -0.61
    mol
    -0.61
    âĺħâĺħ
    -0.60
    POSITIVE LOGITS
    iating
    1.79
    iates
    1.52
     kinds
    1.43
    iations
    1.32
    ials
    1.30
     types
    1.22
    iated
    1.17
    iator
    1.16
     versions
    1.12
    iation
    1.07
    Activations Density 0.037%

    No Known Activations