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. 7364
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs related to capabilities and skills

    oai_token-act-pair · gpt-3.5-turbo

    expressions of ability or capacity to perform actions

    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
    soDeliveryDate
    -0.84
    cloth
    -0.77
    mails
    -0.74
    boxing
    -0.72
    furt
    -0.72
    listed
    -0.72
    ;;;;;;;;;;;;
    -0.68
    DAQ
    -0.68
     Brut
    -0.66
    ilyn
    -0.66
    POSITIVE LOGITS
     communicate
    1.25
     manipulate
    1.16
     navigate
    1.15
     engage
    1.13
     achieve
    1.12
     accumulate
    1.12
     generate
    1.09
     acquire
    1.08
     absorb
    1.08
     improve
    1.07
    Activations Density 0.095%

    No Known Activations