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. 8-RES-JB
    6. 18160
    Prev
    Next
    INDEX
    Explanations

    the verb "do" being used in sentences

    oai_token-act-pair · gpt-3.5-turbo

    statements about people's actions and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Entered
    -0.65
     Dise
    -0.63
     Hok
    -0.63
    case
    -0.61
     Ages
    -0.60
     Resolution
    -0.59
    fields
    -0.58
     Panzer
    -0.57
     Islands
    -0.57
     Madagascar
    -0.56
    POSITIVE LOGITS
    pez
    1.08
    omsday
    1.02
    ppel
    0.98
    zed
    0.90
    herty
    0.90
    oms
    0.89
    vet
    0.89
    gging
    0.86
     not
    0.86
    ggy
    0.84
    Activations Density 0.150%

    No Known Activations