INDEX

Explanations

instances of conditional language or terms related to uncertainty and limitations in software guarantees

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 neceff

-0.64

 ſte

-0.64

 purpoſe

-0.62

 ſta

-0.62

ſelf

-0.60

 ſever

-0.60

 tranſ

-0.60

 Theſe

-0.60

 ſtate

-0.59

ؤلاء

-0.58

POSITIVE LOGITS

 even

4.11

even

3.54

Even

3.01

 Even

2.98

 sogar

2.96

 даже

2.91

 persino

2.86

 EVEN

2.81

 incluso

2.79

 навіть

2.78

Activations Density 0.531%

instances of conditional language or terms related to uncertainty and limitations in software guarantees

No Comments

No Known Activations