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. 18564
    Prev
    Next
    INDEX
    Explanations

    complex relationships or situations where something is hidden or under layers

    oai_token-act-pair · gpt-3.5-turbo

    references to concealment and hidden activities

    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
     educ
    -0.69
     vetoed
    -0.68
     attendance
    -0.67
     buyer
    -0.67
    IFIED
    -0.66
     geared
    -0.64
     illust
    -0.64
     honorary
    -0.64
     boycot
    -0.63
    ocal
    -0.62
    POSITIVE LOGITS
     depths
    1.20
     bushes
    1.18
     trenches
    1.15
     mountains
    1.13
     cliffs
    1.12
     tunnels
    1.12
     woods
    1.08
     canyon
    1.08
     caves
    1.07
     Mountains
    1.06
    Activations Density 0.722%

    No Known Activations