© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23707
    Prev
    Next
    INDEX
    Explanations

    references to astronomical objects and phenomena

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cosmic phenomena and astronomical objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iquette
    -0.90
    ufact
    -0.86
    iability
    -0.79
    CVE
    -0.73
    inical
    -0.73
    IGHTS
    -0.71
    alach
    -0.70
    atha
    -0.70
    edience
    -0.70
    ilitation
    -0.69
    POSITIVE LOGITS
     galaxies
    1.41
     planets
    1.35
     asteroids
    1.33
     galaxy
    1.26
     neutron
    1.23
     satellites
    1.21
     cosmic
    1.19
     stars
    1.17
     interstellar
    1.17
     asteroid
    1.15
    Activations Density 0.159%

    No Known Activations