© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3093
    Prev
    Next
    INDEX
    Explanations

    words related to deriving benefits or advantages

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating some form of benefit or advantage

    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
    aval
    -0.59
     potato
    -0.59
     faults
    -0.59
    cerning
    -0.58
     Traps
    -0.58
    amb
    -0.56
    OVA
    -0.56
     nucle
    -0.55
     garage
    -0.54
     smokes
    -0.54
    POSITIVE LOGITS
    iciary
    0.93
    benefit
    0.89
    doms
    0.88
    ĸļ
    0.83
    emale
    0.82
    onies
    0.80
     financially
    0.76
     benefiting
    0.74
    Marginal
    0.74
    CHAT
    0.73
    Activations Density 0.033%

    No Known Activations