Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 12978
    Prev
    Next
    INDEX
    Explanations

    verbs that are emphasizing a particular action or sentiment

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to affirmations and confirmations

    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
    è¦ļéĨĴ
    -0.61
     respectively
    -0.61
    SPONSORED
    -0.60
    abal
    -0.60
    arth
    -0.60
    ]).
    -0.60
     guiActiveUnfocused
    -0.60
    trump
    -0.59
    berra
    -0.58
    igious
    -0.58
    POSITIVE LOGITS
    oret
    0.70
    adays
    0.52
    neath
    0.51
    Especially
    0.49
     Xen
    0.48
     sure
    0.48
    cknowled
    0.46
     Vulcan
    0.46
     kidding
    0.46
     Kru
    0.45
    Activations Density 0.780%

    No Known Activations