© 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. 6-RES-JB
    11. 4215
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ensuring or confirming actions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "make sure."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PsyNetMessage
    -0.69
    HF
    -0.69
    æ©
    -0.68
     Cosponsors
    -0.67
     ç¥ŀ
    -0.67
    Rated
    -0.64
    anon
    -0.64
     Zig
    -0.62
    alter
    -0.61
     Variant
    -0.59
    POSITIVE LOGITS
    ariat
    0.66
     valve
    0.65
    ties
    0.63
    erest
    0.63
    hea
    0.62
     customers
    0.61
     fertil
    0.61
     everybody
    0.61
    imaru
    0.61
    jobs
    0.59
    Activations Density 0.033%

    No Known Activations