INDEX

Explanations

phrases that indicate conditions or limitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

OGND

-1.08

 Paglinawan

-1.03

CWE

-1.02

TagMode

-0.98

__':

-0.98

 propOrder

-0.95

 Audiodateien

-0.94

uxxxx

-0.93

 myſelf

-0.93

 zvuky

-0.92

POSITIVE LOGITS

 also

1.06

0.84

 likewise

0.70

also

0.66

was

0.64

is

0.62

 أيضاً

0.62

...

0.62

0.59

Activations Density 1.432%

phrases that indicate conditions or limitations

No Comments

No Known Activations