INDEX

Explanations

quantitative measurements and comparisons in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 impactful

-0.96

 incentiv

-0.93

 leveraging

-0.87

 proactively

-0.86

 Importantly

-0.85

 showcased

-0.84

 Notably

-0.83

-0.82

 upfront

-0.81

 microbiome

-0.81

POSITIVE LOGITS

faßt

0.79

 daß

0.77

 muß

0.66

 Negroes

0.64

 läßt

0.62

asmuch

0.60

 apparently

0.60

luß

0.59

 mengadakan

0.59

 Daß

0.58

Activations Density 2.190%

quantitative measurements and comparisons in scientific contexts

No Comments

No Known Activations