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. 7-RES-JB
    6. 6178
    Prev
    Next
    INDEX
    Explanations

    entities that are considered essential or characteristic of a particular context or environment

    oai_token-act-pair · gpt-3.5-turbo

    references to essential or foundational elements 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
    sterdam
    -0.98
    odore
    -0.92
    TPPStreamerBot
    -0.87
    oÄŁ
    -0.85
    thur
    -0.84
    jri
    -0.81
    otos
    -0.78
    vernment
    -0.77
    aline
    -0.76
    hap
    -0.75
    POSITIVE LOGITS
     staple
    0.86
     staples
    0.86
    stay
    0.82
    weights
    0.74
    tenance
    0.74
    belt
    0.72
    stones
    0.69
    fields
    0.68
     Breaker
    0.67
     whipping
    0.67
    Activations Density 0.043%

    No Known Activations