© 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. 8-RES-JB
    11. 6848
    Prev
    Next
    INDEX
    Explanations

    words related to outer space exploration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to outer space and space exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inger
    -0.73
     Snyder
    -0.69
    UCT
    -0.68
    ause
    -0.65
    usted
    -0.64
     Rove
    -0.64
     presumptive
    -0.64
     Brow
    -0.63
    otine
    -0.62
    irez
    -0.62
    POSITIVE LOGITS
    flight
    1.22
    plane
    0.96
     shuttle
    0.94
    gravity
    0.94
    craft
    0.92
    Engineers
    0.88
    planes
    0.87
    kat
    0.86
    borne
    0.84
    uits
    0.84
    Activations Density 0.036%

    No Known Activations