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. 2287
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Ch" followed by a single-digit or two-digit number

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to a specific name or term that begins with "Ch."

    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
    WARD
    -0.83
     lockout
    -0.77
     Reloaded
    -0.77
    ITED
    -0.73
     visitation
    -0.70
    PLIED
    -0.66
    è»
    -0.66
    ãĤ´ãĥ³
    -0.66
    ENCE
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.64
    POSITIVE LOGITS
    amps
    1.18
    isel
    1.15
    aos
    1.14
    unks
    1.08
    illing
    1.08
    annels
    1.07
    ivalry
    1.05
    owder
    1.04
    orus
    1.04
    amber
    1.02
    Activations Density 0.029%

    No Known Activations