Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15547
    Prev
    Next
    INDEX
    Explanations

    German names or titles

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the name "von" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ional
    -0.84
     procedural
    -0.75
    UGC
    -0.74
    atari
    -0.71
    taboola
    -0.67
    Canadian
    -0.66
    mable
    -0.66
    wives
    -0.66
    orph
    -0.64
    ointment
    -0.63
    POSITIVE LOGITS
     Braun
    1.11
    neg
    0.90
     der
    0.88
     Syd
    0.87
     Frey
    0.87
     Kra
    0.85
     Wer
    0.83
     Doom
    0.82
     Stru
    0.82
     Schwarz
    0.81
    Activations Density 0.044%

    No Known Activations