© 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. 9-RES-JB
    11. 16289
    Prev
    Next
    INDEX
    Explanations

    mentions of the composer Beethoven

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the composer Beethoven

    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
     glide
    -0.68
     controlling
    -0.64
     drift
    -0.63
     excise
    -0.63
     puzzle
    -0.61
     pole
    -0.59
     constellation
    -0.59
     firsthand
    -0.58
     totality
    -0.58
    姫
    -0.58
    POSITIVE LOGITS
    hemoth
    1.34
    yond
    1.19
    arer
    1.19
    zos
    1.15
    arded
    1.13
    arers
    1.12
    aum
    1.12
    cca
    1.12
    agle
    1.11
    ijing
    1.10
    Activations Density 0.021%

    No Known Activations