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. 15975
    Prev
    Next
    INDEX
    Explanations

    the infinitive form of verbs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "decided to."

    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
     Detected
    -0.83
     IMAGES
    -0.75
    listed
    -0.73
    thumbnails
    -0.67
     reperto
    -0.65
     terminals
    -0.64
    database
    -0.64
     Explan
    -0.64
    points
    -0.63
    Lear
    -0.63
    POSITIVE LOGITS
     settle
    1.24
     pursue
    1.13
     postpone
    1.10
     incorporate
    1.04
     give
    1.03
     revisit
    1.02
     ignore
    1.00
     explore
    0.99
     donate
    0.98
     capitalize
    0.97
    Activations Density 0.077%

    No Known Activations