© 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. 8-RES-JB
    11. 16742
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "Hunt" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the word "Hun" in various contexts

    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
    ONS
    -0.72
    henko
    -0.66
    ographically
    -0.66
     responsive
    -0.61
    OND
    -0.60
    ruption
    -0.60
    USE
    -0.60
    ussen
    -0.59
     Hof
    -0.59
    aux
    -0.58
    POSITIVE LOGITS
    kered
    1.24
    ters
    1.07
    ned
    1.06
    cheon
    1.02
    ting
    1.00
    ches
    0.98
    ted
    0.97
    ger
    0.96
    ched
    0.90
    ãĤ§
    0.89
    Activations Density 0.042%

    No Known Activations