INDEX

Explanations

terms related to polarity and polling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

webElementGuid

-1.04

rungsseite

-1.03

 doInBackground

-0.94

 EdgeInsets

-0.93

expandindo

-0.89

WebVitals

-0.89

CppMethod

-0.87

GIVEREF

-0.86

ніципалі

-0.86

 للاسماء

-0.84

POSITIVE LOGITS

 Poll

1.61

 Poles

1.59

 poll

1.57

pol

1.56

pol

1.50

 POLL

1.50

Poll

1.48

 Pole

1.48

poll

1.48

POL

1.48

Activations Density 0.106%

terms related to polarity and polling

No Comments

No Known Activations