INDEX

Explanations

terms related to safety in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AddTagHelper

-0.71

 صوتيه

-0.59

ArrowToggle

-0.57

ends

-0.56

IsContent

-0.52

 otomatig

-0.52

enerbah

-0.51

 natale

-0.50

ensatz

-0.49

 sval

-0.49

POSITIVE LOGITS

 precautions

0.74

 concerns

0.72

 considerations

0.67

 precau

0.66

 precaution

0.64

concerns

0.63

rawDesc

0.62

afety

0.62

 measures

0.61

 MEASURES

0.61

Activations Density 0.070%

terms related to safety in various contexts

No Comments

No Known Activations