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. 0-RES-JB
    6. 7239
    Prev
    Next
    INDEX
    Explanations

    phrases related to binding or connecting things together

    oai_token-act-pair · gpt-3.5-turbo

    terms related to binding or connections in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilo
    -0.70
     Upton
    -0.69
     visitation
    -0.66
    CTV
    -0.65
    mosp
    -0.65
     Atmosp
    -0.64
    aton
    -0.63
    ippi
    -0.63
     McM
    -0.63
     Spike
    -0.62
    POSITIVE LOGITS
     bind
    3.91
     binds
    2.62
    bind
    2.34
     Bind
    2.32
    Bind
    1.96
     bindings
    1.63
     bound
    1.48
     binding
    1.48
     Binding
    1.29
    binding
    1.21
    Activations Density 0.021%

    No Known Activations