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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 17345
    Prev
    Next
    INDEX
    Explanations

    phrases related to official confirmations or denials

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and markers indicating sentence boundaries or structural elements in text

    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
    âķIJ
    -0.47
     quir
    -0.46
    )?
    -0.46
    =-=-=-=-
    -0.45
     Kes
    -0.43
    sung
    -0.43
     Krypt
    -0.42
    OTS
    -0.42
    --------------------------------
    -0.42
     Cavs
    -0.42
    POSITIVE LOGITS
    arij
    0.59
    dinand
    0.52
    inational
    0.52
    ewater
    0.49
    htaking
    0.46
     culminated
    0.45
    glers
    0.44
    anwhile
    0.44
    apeshifter
    0.43
    evidence
    0.43
    Activations Density 1.879%

    No Known Activations