© 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. 11-RES-JB
    11. 18654
    Prev
    Next
    INDEX
    Explanations

    words related to legal matters and procedures

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to emotions and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ca
    -0.76
    tons
    -0.74
    hens
    -0.73
    etsk
    -0.73
    fully
    -0.73
    ties
    -0.73
    ghai
    -0.72
    come
    -0.71
    kish
    -0.71
    tery
    -0.71
    POSITIVE LOGITS
    OUN
    1.69
    AND
    1.65
    AMES
    1.64
    ALE
    1.64
    URR
    1.63
    ORT
    1.62
    ORD
    1.62
    ATH
    1.62
    ENT
    1.62
    IGHTS
    1.62
    Activations Density 0.173%

    No Known Activations