INDEX

Explanations

phrases and terms related to maximum values or limits

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-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

 jdbcTemplate

-0.60

 Hessian

-0.57

thansa

-0.57

tvguidetime

-0.56

 Teeth

-0.56

 deflation

-0.56

hoka

-0.54

oflavin

-0.54

Vog

-0.53

Implement

-0.52

POSITIVE LOGITS

CodeAttribute

0.65

SharedDtor

0.54

remp

0.52

ẾT

0.51

 թվական

0.51

 kaarangay

0.50

EndContext

0.50

Datuak

0.50

 cuantos

0.50

Enllaços

0.50

Activations Density 0.034%

phrases and terms related to maximum values or limits

No Comments

No Known Activations