© 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. 3-RES-JB
    11. 22677
    Prev
    Next
    INDEX
    Explanations

    mentions of the celestial body "Titan" in space-related contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Titan," indicating a focus on large entities or concepts, particularly in various contexts such as space, media, or sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ournal
    -0.69
    cation
    -0.68
    travel
    -0.67
    eal
    -0.64
    ealing
    -0.64
     Dise
    -0.63
    cause
    -0.63
    living
    -0.62
    mph
    -0.62
    ll
    -0.61
    POSITIVE LOGITS
    fall
    1.00
     Titan
    0.87
    arium
    0.83
    omach
    0.82
    osaurs
    0.80
    ica
    0.79
    icum
    0.78
    agraph
    0.74
    oton
    0.74
     Amon
    0.72
    Activations Density 0.012%

    No Known Activations