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. 17056
    Prev
    Next
    INDEX
    Explanations

    instances where something transitions from one state to another

    oai_token-act-pair · gpt-3.5-turbo

    the word "from" in various contexts

    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
    perture
    -0.87
    insula
    -0.79
    iosyn
    -0.76
    Mask
    -0.75
    gemony
    -0.73
    sylv
    -0.73
    catentry
    -0.73
    quote
    -0.71
    iquette
    -0.71
    mask
    -0.71
    POSITIVE LOGITS
     afar
    1.05
     whence
    0.81
     abroad
    0.80
     somewhere
    0.80
     scratch
    0.77
     anywhere
    0.74
     nowhere
    0.74
     across
    0.71
     wherever
    0.68
     obscurity
    0.68
    Activations Density 0.059%

    No Known Activations