© 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. 20255
    Prev
    Next
    INDEX
    Explanations

    mentions of legal language and agreements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the symbol sequence "<|endoftext|>"

    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
    OGR
    -0.66
    onsequ
    -0.63
     numb
    -0.63
    agy
    -0.62
    REF
    -0.62
    osen
    -0.60
    Quantity
    -0.59
    abul
    -0.59
    llah
    -0.58
    abre
    -0.57
    POSITIVE LOGITS
    ighth
    0.66
     Concord
    0.64
     homes
    0.63
    operated
    0.59
    atern
    0.58
    ãĥĩ
    0.58
     Prop
    0.57
    ongyang
    0.56
     dearly
    0.56
     Confederate
    0.56
    Activations Density 0.154%

    No Known Activations