© 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. 1-RES-JB
    11. 19627
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cannibal" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cannibalism and butchery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.80
    UE
    -0.76
    URI
    -0.75
    Correct
    -0.72
    UV
    -0.72
    CLASS
    -0.70
     concess
    -0.68
    kt
    -0.67
    RAY
    -0.67
    yon
    -0.66
    POSITIVE LOGITS
     cannibal
    1.01
    icate
    0.93
    ibal
    0.92
    phabet
    0.92
     Corpse
    0.88
     Cann
    0.86
     cann
    0.83
    icating
    0.79
    thia
    0.78
    ictions
    0.76
    Activations Density 0.012%

    No Known Activations