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. 24015
    Prev
    Next
    INDEX
    Explanations

    words related to lacking or absence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a deficiency or absence of something

    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
    dry
    -0.67
    escal
    -0.64
    tainment
    -0.63
    alty
    -0.62
    eve
    -0.62
    dr
    -0.60
    selves
    -0.60
    flo
    -0.60
    Pacific
    -0.58
    oos
    -0.58
    POSITIVE LOGITS
    lust
    1.02
    luster
    0.88
    lessly
    0.75
     willpower
    0.71
    vre
    0.70
     miser
    0.69
    avorite
    0.69
     hesitation
    0.69
     patience
    0.68
    minded
    0.66
    Activations Density 0.024%

    No Known Activations