© 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. 20076
    Prev
    Next
    INDEX
    Explanations

    words related to advanced technology and equipment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to advanced technology and equipment

    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
    Fest
    -0.77
    fest
    -0.76
    alla
    -0.71
    Fall
    -0.71
    arenthood
    -0.70
    eny
    -0.70
    cember
    -0.69
    Season
    -0.69
     Disciple
    -0.69
    é»Ĵ
    -0.69
    POSITIVE LOGITS
     detectors
    1.30
     apparatus
    1.22
     automated
    1.19
     monitors
    1.18
     sensors
    1.17
     mechanisms
    1.16
     mechanism
    1.14
     scanners
    1.12
     detector
    1.10
     safeguards
    1.09
    Activations Density 1.408%

    No Known Activations