© 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. 2-RES-JB
    11. 8436
    Prev
    Next
    INDEX
    Explanations

    references to specific celestial bodies or astronomical phenomena

    oai_token-act-pair · gpt-3.5-turbo

    references to significant astronomical objects and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Palestin
    -0.74
    ãĤ¢ãĥ«
    -0.71
    åĭ
    -0.70
    Employ
    -0.70
    ãĥīãĥ©
    -0.70
    ãĤ¨ãĥ«
    -0.68
    foreign
    -0.65
    nec
    -0.65
    --------------------------------------------------------
    -0.65
    inelli
    -0.64
    POSITIVE LOGITS
     orbiting
    0.96
    autical
    0.89
    oidal
    0.88
     astronomers
    0.86
     astronomer
    0.86
     telescope
    0.85
     Collider
    0.84
     physicist
    0.83
     Telescope
    0.82
     Observatory
    0.81
    Activations Density 0.200%

    No Known Activations