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. 6-RES-JB
    6. 18554
    Prev
    Next
    INDEX
    Explanations

    words related to importance or necessity

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with essentiality and significance

    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
    uthor
    -0.69
    intend
    -0.65
    shirt
    -0.62
    çİĭ
    -0.62
    orks
    -0.61
    avy
    -0.61
    eely
    -0.60
    Flight
    -0.59
    elf
    -0.59
    uclear
    -0.59
    POSITIVE LOGITS
     enough
    0.90
     ingred
    0.76
     deterrent
    0.76
     nonetheless
    0.76
     adjunct
    0.75
     integral
    0.75
     distingu
    0.74
     undermin
    0.74
     motivating
    0.70
     motiv
    0.70
    Activations Density 0.098%

    No Known Activations