INDEX

Explanations

variations of the word "false" and related terms

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

Portail

-0.79

 InputDecoration

-0.77

AndEndTag

-0.77

DockStyle

-0.75

MigrationBuilder

-0.74

withIdentifier

-0.74

 Paglinawan

-0.74

ReusableCell

-0.73

IntoConstraints

-0.71

kloped

-0.70

POSITIVE LOGITS

fal

0.91

Fal

0.81

Fal

0.78

bukkit

0.66

fal

0.61

 Falcons

0.59

FAL

0.52

 falcon

0.50

medriver

0.49

 Falken

0.48

Activations Density 0.070%

variations of the word "false" and related terms

No Comments

No Known Activations