© 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. 7-RES-JB
    11. 13574
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreeing to terms or conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to opting in or out of subscriptions and agreements

    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
     mach
    -0.70
    ilver
    -0.69
     Enix
    -0.64
    igans
    -0.63
    andowski
    -0.62
     intrins
    -0.61
     mole
    -0.61
     Mach
    -0.60
    urgy
    -0.59
     homebrew
    -0.59
    POSITIVE LOGITS
    Submit
    0.71
    Subscribe
    0.69
    google
    0.67
    endment
    0.66
    thia
    0.64
    repeat
    0.64
    icides
    0.63
    Finish
    0.63
    depending
    0.62
    separ
    0.62
    Activations Density 0.051%

    No Known Activations