© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 2105
    Prev
    Next
    INDEX
    Explanations

    references to the celestial body "Titan"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Titan" and related contexts, including both celestial and fictional entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lly
    -0.67
    cation
    -0.67
    enez
    -0.66
    ournal
    -0.66
    travel
    -0.65
    PLE
    -0.63
    --------------------------------------------------------
    -0.62
    cause
    -0.62
    dit
    -0.62
    Keefe
    -0.61
    POSITIVE LOGITS
    fall
    1.15
    arium
    0.94
    omach
    0.93
    osaurs
    0.90
    ica
    0.84
    oid
    0.80
    itans
    0.77
    oton
    0.77
    agraph
    0.76
    ICS
    0.76
    Activations Density 0.034%

    No Known Activations