INDEX

Explanations

terms related to depth and topography 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

$",

-0.69

дже

-0.64

 nieder

-0.64

hot

-0.64

)|^{

-0.63

 Giovan

-0.61

 Silverman

-0.61

Caw

-0.61

 Cowan

-0.59

mainAxisSize

-0.57

POSITIVE LOGITS

 depth

2.00

 DEPTH

1.94

 Depth

1.93

Depth

1.87

depth

1.79

DEPTH

1.66

 depths

1.53

 profundidad

1.03

 глуби

1.02

 profondeur

0.96

Activations Density 0.104%

terms related to depth and topography in various contexts

No Comments

No Known Activations