© 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. 10-RES-JB
    11. 12245
    Prev
    Next
    INDEX
    Explanations

    the word "spin" followed by a hyphen and a positive number representing a connection to a derivative or related concept

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "spin" or phrases that indicate a spin-off concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mellon
    -0.80
     Scores
    -0.69
     Frie
    -0.65
     Newsp
    -0.63
     Crate
    -0.62
     Aud
    -0.61
     Alma
    -0.59
     Cah
    -0.59
     Highlander
    -0.58
    xual
    -0.58
    POSITIVE LOGITS
    ners
    1.49
    eless
    1.21
    offs
    1.14
    off
    1.06
    wheel
    1.01
    ned
    0.98
    othal
    0.96
    ster
    0.89
    tails
    0.88
    uten
    0.83
    Activations Density 0.031%

    No Known Activations