INDEX

Explanations

various layout and styling attributes in a coding context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 strerror

-0.71

 himo

-0.70

httphttps

-0.68

 nakalista

-0.67

contentLoaded

-0.66

ühner

-0.64

 tartalomajánló

-0.60

uxxxx

-0.59

})`

-0.58

ázquez

-0.58

POSITIVE LOGITS

row

1.50

row

1.13

Row

1.05

ROW

1.04

Row

0.89

RectangleBorder

0.71

ROW

0.69

ROWS

0.67

rows

0.63

rower

0.59

Activations Density 0.027%

various layout and styling attributes in a coding context

No Comments

No Known Activations