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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 17173
    Prev
    Next
    INDEX
    Explanations

    adjectives related to tasks and situations that are challenging or causing disagreements

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with tedious and contentious tasks or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iphate
    -0.78
    nosis
    -0.71
    iph
    -0.70
    ortal
    -0.69
    ablishment
    -0.68
    ebus
    -0.67
    amph
    -0.67
    icts
    -0.66
    isphere
    -0.65
    rongh
    -0.65
    POSITIVE LOGITS
    intensive
    0.73
     Ago
    0.72
     tedious
    0.70
     advers
    0.67
     messy
    0.64
    rament
    0.63
     comb
    0.63
     ardu
    0.63
     costly
    0.62
     expensive
    0.62
    Activations Density 0.037%

    No Known Activations