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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 9037
    Prev
    Next
    INDEX
    Explanations

    things related to legal and investigative procedures, such as registering FIRs

    oai_token-act-pair · gpt-3.5-turbo

    instances of time-related references in events or narratives

    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
     destro
    -0.63
    senal
    -0.58
     advoc
    -0.57
     eleph
    -0.56
    acebook
    -0.55
     nodd
    -0.53
     outwe
    -0.52
    emale
    -0.52
     corrid
    -0.52
    akespe
    -0.52
    POSITIVE LOGITS
     Shutdown
    0.46
    HOU
    0.44
     Background
    0.43
    !--
    0.42
    flush
    0.42
    BLIC
    0.41
     Marvel
    0.40
    catentry
    0.40
     Introduction
    0.40
     Judicial
    0.40
    Activations Density 1.242%

    No Known Activations