INDEX

Explanations

terms related to visibility or seeing

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

astify

-0.76

aarrggbb

-0.71

__':

-0.70

")));

-0.66

InputTagHelper

-0.64

 snippetHide

-0.64

✨:

-0.64

 cork

-0.63

 propOrder

-0.63

neurial

-0.63

POSITIVE LOGITS

vis

0.77

Vis

0.75

vis

0.68

Vis

0.66

VIS

0.54

 VIAF

0.49

 Reverso

0.47

 viso

0.45

à

0.43

VIS

0.43

Activations Density 0.101%

terms related to visibility or seeing

No Comments

No Known Activations