INDEX

Explanations

occurrences of the word "to" indicating purpose or intention

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_4/width_65k/average_l0_66

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.4.hook_mlp_out

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

 also

-0.48

 char

-0.47

-0.46

-0.45

 version

-0.44

-0.43

char

-0.43

গ্রহ

-0.43

せい

-0.42

POSITIVE LOGITS

 resourceCulture

0.90

 fotografico

0.89

 againſt

0.88

queryInterface

0.87

 itſelf

0.84

Efq

0.84

 CreateTagHelper

0.81

 Majefty

0.81

Diwedd

0.81

 Monfieur

0.81

Activations Density 0.013%

occurrences of the word "to" indicating purpose or intention

No Comments

No Known Activations