© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 20268
    Prev
    Next
    INDEX
    Explanations

    mentions of a lack or absence of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lack" in relation to various issues or problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Goes
    -0.70
    posts
    -0.66
    oti
    -0.62
    quished
    -0.59
    vale
    -0.59
    uments
    -0.59
    planes
    -0.58
    oto
    -0.58
    ozo
    -0.58
    adj
    -0.58
    POSITIVE LOGITS
     lack
    3.68
     inability
    2.25
     Lack
    1.93
     absence
    1.84
     lacks
    1.79
     lacked
    1.77
     inexper
    1.76
     unwillingness
    1.73
     lacking
    1.70
     shortage
    1.70
    Activations Density 0.024%

    No Known Activations