© 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. 10-RES-JB
    11. 8122
    Prev
    Next
    INDEX
    Explanations

    words related to food and beverage

    oai_token-act-pair · gpt-3.5-turbo

    instances of various terms related to specific entries or elements within a list or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.79
     Pwr
    -0.74
    Īè
    -0.65
    ãĥķãĤ©
    -0.61
    -+
    -0.60
    å°Ĩ
    -0.60
    Reviewer
    -0.59
    REF
    -0.58
    ĥ
    -0.58
     soph
    -0.58
    POSITIVE LOGITS
    imus
    0.93
    ipeg
    0.88
    neau
    0.85
    emen
    0.84
    fulness
    0.78
    erd
    0.77
    ickey
    0.75
    elly
    0.74
    bilt
    0.74
    sworth
    0.74
    Activations Density 0.095%

    No Known Activations