© 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. 7-RES-JB
    11. 16789
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or official matters

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing skepticism or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.30
     rul
    -0.27
     territ
    -0.26
     Azerb
    -0.24
     conclud
    -0.23
     furthermore
    -0.23
    enegger
    -0.22
     moreover
    -0.22
     horizont
    -0.21
     manif
    -0.21
    POSITIVE LOGITS
    ratom
    0.25
    taboola
    0.20
    osures
    0.19
    SI
    0.19
    IGHTS
    0.18
    ANE
    0.18
    yrights
    0.18
    AK
    0.17
    OFF
    0.17
    ISC
    0.17
    Activations Density 5.534%

    No Known Activations