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. 6-RES-JB
    6. 10532
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial costs or value

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of accumulation or increase

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kirby
    -0.74
     Crime
    -0.63
     Casino
    -0.63
     Motors
    -0.63
     Racing
    -0.61
     Cage
    -0.59
     Barber
    -0.59
     Hammer
    -0.59
     Technique
    -0.59
     Catalyst
    -0.58
    POSITIVE LOGITS
    grown
    0.83
     excess
    0.75
    undreds
    0.72
     gallons
    0.70
    units
    0.69
     quantities
    0.69
    animate
    0.69
     scraps
    0.68
     chunks
    0.68
    untled
    0.67
    Activations Density 0.145%

    No Known Activations