© 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. 19649
    Prev
    Next
    INDEX
    Explanations

    fragments of words related to the name 'Emily'

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "ily" indicating a focus on expressions of affection or positivity

    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
    etter
    -0.70
    ivity
    -0.69
    hesis
    -0.68
    itivity
    -0.68
     Crus
    -0.65
    igo
    -0.64
     Settlement
    -0.64
    eport
    -0.64
    raviolet
    -0.62
    orical
    -0.62
    POSITIVE LOGITS
    abal
    0.84
    abba
    0.80
    ibrary
    0.72
    adow
    0.72
     nerv
    0.71
    ãĤ©
    0.69
    clad
    0.68
    metry
    0.67
    stals
    0.66
    adows
    0.65
    Activations Density 0.019%

    No Known Activations