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. 603
    Prev
    Next
    INDEX
    Explanations

    word pairs related to reasoning and cause-and-effect

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve relationships and connections between concepts or entities

    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
    kees
    -0.99
    ubes
    -0.78
    urs
    -0.77
    ppo
    -0.76
    itled
    -0.75
    scribe
    -0.74
    ãĤº
    -0.74
    bernatorial
    -0.74
    kiss
    -0.73
    osta
    -0.72
    POSITIVE LOGITS
     inertia
    0.95
     ingenuity
    0.93
     intuition
    0.93
     circumst
    0.87
     factors
    0.87
     inexper
    0.87
     sheer
    0.87
     negligence
    0.86
     anecdotal
    0.86
     observations
    0.82
    Activations Density 0.383%

    No Known Activations