INDEX

Explanations

instances of the word "at" 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

]),

-1.00

^(@)

-0.99

 незавершена

-0.94

NewUrlParser

-0.94

 Vikipedi

-0.93

 iſt

-0.92

 FetchType

-0.91

iffion

-0.89

 فريبيس

-0.89

 IBRARY

-0.89

POSITIVE LOGITS

at

0.77

↵

0.68

AT

0.67

↵↵

0.66

At

0.65

At

0.63

The

0.60

in

0.59

The

0.57

0.56

Activations Density 0.221%

instances of the word "at" in various contexts

No Comments

No Known Activations