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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 16472
    Prev
    Next
    INDEX
    Explanations

    details related to laws or regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases concerning social policies and discrimination issues

    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
    itiveness
    -0.60
    Drag
    -0.60
    polit
    -0.56
    âĦ¢:
    -0.55
    \":
    -0.54
     nutshell
    -0.50
    omics
    -0.50
    ISS
    -0.49
    atch
    -0.49
    gem
    -0.48
    POSITIVE LOGITS
     beware
    0.65
    instead
    0.64
     instead
    0.56
    anwhile
    0.55
     CHO
    0.53
     thereby
    0.53
    entimes
    0.52
     presumably
    0.52
     draining
    0.51
     soaking
    0.50
    Activations Density 1.970%

    No Known Activations