Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 12425
    Prev
    Next
    INDEX
    Explanations

    words related to technical specifications and requirements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical characteristics, structures, and academic qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rencies
    -0.83
    urches
    -0.81
    assies
    -0.73
    doms
    -0.69
     Occupations
    -0.68
    itars
    -0.67
    riages
    -0.67
    tics
    -0.66
     Vehicles
    -0.65
    ernels
    -0.65
    POSITIVE LOGITS
     standpoint
    0.72
    license
    0.70
     sized
    0.70
    abyte
    0.69
    atical
    0.64
     component
    0.63
    ful
    0.63
     sample
    0.62
    ounding
    0.62
     subscription
    0.61
    Activations Density 0.838%

    No Known Activations