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. 9-RES-JB
    6. 8484
    Prev
    Next
    INDEX
    Explanations

    terms related to practicality, tasks, or solutions

    oai_token-act-pair · gpt-3.5-turbo

    references to practicality or practical applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gate
    -0.69
    rican
    -0.68
    ractions
    -0.68
     Furious
    -0.67
    union
    -0.66
    inos
    -0.66
    Roy
    -0.65
    rak
    -0.65
    iba
    -0.65
    enda
    -0.64
    POSITIVE LOGITS
    ity
    1.35
    ities
    1.23
     impossibility
    1.14
     considerations
    1.00
    istically
    0.90
    istic
    0.89
     advice
    0.89
     feasibility
    0.88
     usefulness
    0.87
     necessity
    0.86
    Activations Density 0.058%

    No Known Activations