© 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. 4-RES-JB
    11. 9171
    Prev
    Next
    INDEX
    Explanations

    phrases related to learning or receiving a message

    oai_token-act-pair · gpt-3.5-turbo

    references to lessons learned or educational messages

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

    No Comments

    Negative Logits
    ractive
    -0.72
    idays
    -0.69
     occupancy
    -0.68
    bably
    -0.68
     tighter
    -0.67
    ecided
    -0.66
    rencies
    -0.66
    rosso
    -0.66
    conn
    -0.65
    berman
    -0.64
    POSITIVE LOGITS
     Learned
    1.13
     lessons
    1.13
    Lear
    1.08
     Teach
    1.07
     lesson
    1.06
     Lessons
    0.97
    learn
    0.88
     taught
    0.85
     Lear
    0.81
     learnt
    0.79
    Activations Density 0.024%

    No Known Activations