© 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. 8-RES-JB
    11. 7659
    Prev
    Next
    INDEX
    Explanations

    phrases urging to investigate or examine something

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the verb "look."

    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
    theless
    -0.66
    Cele
    -0.65
    cffff
    -0.58
    cape
    -0.57
    âĹ¼
    -0.56
    CENT
    -0.56
    kson
    -0.55
    ä¹
    -0.55
    Skill
    -0.55
     Palestin
    -0.55
    POSITIVE LOGITS
    ahead
    0.96
    izons
    0.85
     favorably
    0.79
     suspic
    0.77
    ression
    0.77
    ãĤ¶
    0.76
     forward
    0.72
     into
    0.71
    ocene
    0.69
     closely
    0.69
    Activations Density 0.073%

    No Known Activations