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. 19750
    Prev
    Next
    INDEX
    Explanations

    verbs in the past tense related to prior planning or intention

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "planned."

    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
    ienced
    -0.81
    ĪĴ
    -0.78
    upon
    -0.76
    ysis
    -0.74
    bour
    -0.71
    assi
    -0.71
    gars
    -0.70
    Reviewer
    -0.70
    aina
    -0.70
    yards
    -0.70
    POSITIVE LOGITS
     Parenthood
    1.30
    paren
    0.96
     pregnancies
    0.93
     obs
    0.83
     gestation
    0.78
    escape
    0.77
     meals
    0.76
     trips
    0.76
     rollout
    0.75
    ¶
    0.74
    Activations Density 0.022%

    No Known Activations