© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 12783
    Prev
    Next
    INDEX
    Explanations

    terms related to the German language

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character or significant concept represented by the symbol 'ä'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORED
    -0.66
     Jericho
    -0.64
     kernels
    -0.64
     patched
    -0.63
     actors
    -0.63
     Hodg
    -0.63
     Harmony
    -0.60
    IFIED
    -0.60
     Canary
    -0.59
     Faw
    -0.58
    POSITIVE LOGITS
    inen
    1.22
    nder
    1.15
    ternity
    1.09
    tten
    1.02
    ä
    1.02
    nen
    0.96
    ¢
    0.95
    nsic
    0.91
    si
    0.91
    rn
    0.91
    Activations Density 0.029%

    No Known Activations