© 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. 8-RES-JB
    11. 7000
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "giant" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to large creatures or entities, particularly those described as "giant."

    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
    Not in Any Lists

    No Comments

    Negative Logits
    yrinth
    -0.80
    say
    -0.69
    odore
    -0.67
    rb
    -0.67
    treatment
    -0.67
    schild
    -0.67
    informed
    -0.66
    ties
    -0.66
    qi
    -0.65
    ntax
    -0.65
    POSITIVE LOGITS
     squid
    1.04
     leap
    0.87
     bould
    0.86
     leaps
    0.85
     gorilla
    0.83
     aster
    0.82
     sized
    0.79
     Leap
    0.78
     Squid
    0.78
     eyeb
    0.77
    Activations Density 0.040%

    No Known Activations