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. 4-RES-JB
    6. 18806
    Prev
    Next
    INDEX
    Explanations

    phrases related to practicality and actionable advice

    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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gate
    -0.74
    buck
    -0.73
    essee
    -0.72
    adder
    -0.70
    olen
    -0.69
    inos
    -0.69
    opsis
    -0.67
    rael
    -0.67
    rak
    -0.66
    ocl
    -0.66
    POSITIVE LOGITS
    ity
    1.08
    ities
    0.88
     impossibility
    0.87
     considerations
    0.84
     embodiment
    0.79
    istically
    0.77
     necessities
    0.76
     relevance
    0.74
     necessity
    0.72
     application
    0.71
    Activations Density 0.013%

    No Known Activations