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. 7-RES-JB
    6. 20217
    Prev
    Next
    INDEX
    Explanations

    terms related to evaluation and assessment processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to educational assessments and evaluation processes

    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
    isy
    -0.74
    ewitness
    -0.73
    ãĥĩãĤ£
    -0.71
    zanne
    -0.71
    ified
    -0.71
    zynski
    -0.70
    ifi
    -0.70
    playing
    -0.70
    chi
    -0.69
    inite
    -0.69
    POSITIVE LOGITS
     methods
    0.94
     prowess
    0.94
     mechanisms
    0.93
     techniques
    0.93
     apparatus
    0.89
     schemes
    0.89
     machinery
    0.88
     mechanism
    0.88
     conventions
    0.86
     capabilities
    0.85
    Activations Density 0.280%

    No Known Activations