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. 8887
    Prev
    Next
    INDEX
    Explanations

    concerns, fears, or worries related to potential negative outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to fear and concern about potential negative outcomes

    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
    •layer 8 - fear

    No Comments

    Negative Logits
    aturdays
    -0.76
     commend
    -0.71
     admirable
    -0.71
    hest
    -0.70
    cellence
    -0.66
    thank
    -0.66
    ichick
    -0.66
    except
    -0.65
    oln
    -0.63
     Mondays
    -0.62
    POSITIVE LOGITS
     contam
    1.01
     someday
    1.00
     inadvertently
    0.95
     miscon
    0.95
     misinterpret
    0.94
     repr
    0.91
     jeopard
    0.90
     repercussions
    0.89
     overhe
    0.89
     retribution
    0.87
    Activations Density 0.556%

    No Known Activations