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. 6-RES-JB
    6. 17909
    Prev
    Next
    INDEX
    Explanations

    mentions of populations as numerical figures

    oai_token-act-pair · gpt-3.5-turbo

    references to population statistics and demographics

    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
     omission
    -0.76
     WATCHED
    -0.58
     tactic
    -0.55
     cipher
    -0.55
     delete
    -0.54
     sle
    -0.53
     silence
    -0.53
     missed
    -0.53
     reply
    -0.52
     Offer
    -0.52
    POSITIVE LOGITS
    aceae
    0.86
    wealth
    0.82
    ;;;;;;;;;;;;
    0.72
    idae
    0.70
    ylum
    0.68
    ethnic
    0.68
     kingdoms
    0.67
    sylv
    0.66
    Population
    0.65
    united
    0.65
    Activations Density 1.294%

    No Known Activations