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. 4445
    Prev
    Next
    INDEX
    Explanations

    words related to permanence or irreversible actions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with irreversibility and fundamental changes

    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
    minster
    -0.62
     Archangel
    -0.60
     subconscious
    -0.59
     lapse
    -0.58
     reckoning
    -0.58
    è¦ļéĨĴ
    -0.58
    yip
    -0.58
     Gaga
    -0.57
     upwards
    -0.57
     CLSID
    -0.57
    POSITIVE LOGITS
    ishable
    1.08
    able
    1.02
    ables
    0.98
    enment
    0.96
    ably
    0.92
    ledged
    0.92
    vable
    0.89
    ibilities
    0.88
    ability
    0.86
    ptions
    0.86
    Activations Density 0.142%

    No Known Activations