INDEX

Explanations

terms related to leadership positions and titles in organizations

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

RTEE

-1.00

 MainAxisSize

-0.94

setVerticalGroup

-0.93

MigrationBuilder

-0.92

PyExc

-0.87

AndEndTag

-0.85

 gynhyrchwyd

-0.82

URLException

-0.81

SBATCH

-0.81

最快更新

-0.81

POSITIVE LOGITS

for

0.86

 emeritus

0.67

 responsible

0.64

at

0.59

兼

0.56

 with

0.54

0.53

 designate

0.53

 from

0.52

of

0.51

Activations Density 0.155%

terms related to leadership positions and titles in organizations

No Comments

No Known Activations