INDEX

Explanations

references to additional components or requirements in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

ENDIAN

-0.80

farin

-0.74

 Wikispecies

-0.73

SPATH

-0.73

Климат

-0.68

PYX

-0.66

bufio

-0.64

<?,

-0.60

 régl

-0.60

 arraigned

-0.59

POSITIVE LOGITS

 additional

3.18

additional

2.99

 Additional

2.80

Additional

2.79

 ADDITIONAL

2.58

ADDITIONAL

2.35

 zusätzlichen

2.00

 adicional

1.98

 zusätzliche

1.98

 adicionales

1.91

Activations Density 0.076%

references to additional components or requirements in various contexts

No Comments

No Known Activations