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. 4017
    Prev
    Next
    INDEX
    Explanations

    capital letters in the middle of a sentence signaling a name or title

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'B'

    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
     Gutenberg
    -0.73
     dere
    -0.67
    wcsstore
    -0.66
     choke
    -0.64
     impunity
    -0.63
     glow
    -0.63
     inflic
    -0.61
     Pharaoh
    -0.60
     por
    -0.60
     rpm
    -0.60
    POSITIVE LOGITS
    rief
    1.16
    odies
    1.15
    ETA
    1.11
    anned
    1.08
    ranch
    1.07
    rows
    1.06
    OTH
    1.05
    urt
    1.05
    achel
    1.02
    rug
    1.02
    Activations Density 0.046%

    No Known Activations