© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 22459
    Prev
    Next
    INDEX
    Explanations

    phrases indicating approval or greenlighting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "go" and "do."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dreams
    -0.62
    ĺħ
    -0.62
     symmetry
    -0.60
    $$$$
    -0.60
    undle
    -0.57
    ãģ®é
    -0.57
    RIC
    -0.56
     Provision
    -0.56
    Techn
    -0.55
     Topic
    -0.55
    POSITIVE LOGITS
    ables
    1.07
    ative
    0.88
    orm
    0.88
    ipers
    0.87
    orship
    0.87
    ibles
    0.87
    ings
    0.87
    able
    0.86
    ativity
    0.86
    outs
    0.84
    Activations Density 0.137%

    No Known Activations