INDEX

Explanations

references to political events and activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

aarrggbb

-1.00

PreferredItem

-0.87

CodedInputStream

-0.81

BeginContext

-0.74

Tembelea

-0.72

RectangleBorder

-0.71

 BorderRadius

-0.70

LabelTagHelper

-0.70

 '\\;'

-0.70

ItemBackground

-0.69

POSITIVE LOGITS

0.66

 flurry

0.61

 report

0.59

 spokesman

0.59

 total

0.57

 series

0.53

0.52

 decision

0.52

 massive

0.52

 memorandum

0.52

Activations Density 0.400%

references to political events and activities

No Comments

No Known Activations