Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 10119
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate repeated actions or behavior

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "repeatedly"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.92
    toc
    -0.79
    OTA
    -0.75
    ghai
    -0.73
    soc
    -0.73
    ocene
    -0.71
    istan
    -0.70
    ocard
    -0.68
    mop
    -0.66
    potion
    -0.66
    POSITIVE LOGITS
    theless
    0.87
     repeated
    0.84
     reaff
    0.82
     interrupted
    0.81
     reiter
    0.80
     incarn
    0.79
     unsuccessful
    0.78
     reiterated
    0.78
     contradict
    0.77
     contradicted
    0.77
    Activations Density 0.025%

    No Known Activations