INDEX

Explanations

instances of the word "ex" and its derivatives 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 @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 bezeichneter

-1.18

 مشين

-0.89

 isComment

-0.84

новниш

-0.83

setViewportView

-0.80

THISDAY

-0.79

 uovo

-0.77

paroles

-0.76

 BIBSYS

-0.76

Datuak

-0.76

POSITIVE LOGITS

Extended

0.92

ex

0.90

ex

0.84

Ex

0.84

 Extended

0.80

Ex

0.80

def

0.78

ст

0.71

extended

0.68

 extended

0.68

Activations Density 0.102%

instances of the word "ex" and its derivatives in various contexts

No Comments

No Known Activations