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. 19075
    Prev
    Next
    INDEX
    Explanations

    instances of the word "overly" with varying levels of intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "overly" and related terms that indicate excessiveness

    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
    iens
    -0.79
     Bullets
    -0.77
    igi
    -0.73
     Tycoon
    -0.72
    itudinal
    -0.70
    ians
    -0.70
    raltar
    -0.68
     Rite
    -0.67
    riots
    -0.67
    alion
    -0.66
    POSITIVE LOGITS
     burdens
    0.84
     complicate
    0.82
     optimistic
    0.79
     simplistic
    0.79
    assi
    0.77
     reliant
    0.76
     intoxicated
    0.75
     priced
    0.75
     lax
    0.74
     sensitive
    0.74
    Activations Density 0.017%

    No Known Activations