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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10110
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a full stop

    oai_token-act-pair · gpt-3.5-turbo

    conclusive statements and their supporting details

    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
     dissu
    -0.69
     unloaded
    -0.67
    addons
    -0.66
     bolted
    -0.63
     muster
    -0.62
     tempted
    -0.61
    illac
    -0.61
     outwe
    -0.59
     pesky
    -0.59
    iliary
    -0.59
    POSITIVE LOGITS
    Its
    0.76
    humans
    0.74
     Examples
    0.72
    Contents
    0.71
     Scientists
    0.70
    âĿ
    0.69
    space
    0.67
    Anonymous
    0.66
     Its
    0.66
    dylib
    0.65
    Activations Density 0.701%

    No Known Activations