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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 9815
    Prev
    Next
    INDEX
    Explanations

    titles of songs or albums

    oai_token-act-pair · gpt-3.5-turbo

    instances of proper nouns and significant titles

    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
     podium
    -0.76
     taxp
    -0.73
     PSU
    -0.72
    Jr
    -0.71
     regist
    -0.71
    RM
    -0.67
     workforce
    -0.66
     exch
    -0.65
    SR
    -0.64
    CI
    -0.64
    POSITIVE LOGITS
     Days
    1.01
     Goodbye
    1.01
     Dreams
    1.01
     Passing
    0.99
     Places
    0.98
     Skies
    0.96
     Lies
    0.96
     Yourself
    0.95
     Enough
    0.93
     Falling
    0.92
    Activations Density 0.364%

    No Known Activations