INDEX

Explanations

terms related to the ease or difficulty of processes

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

 transfieras

-0.90

 easy

-0.77

 faciles

-0.73

TagMode

-0.73

easy

-0.69

 itſelf

-0.68

Easy

-0.65

 fácil

-0.65

ſelf

-0.64

 easily

-0.63

POSITIVE LOGITS

 AssemblyTitle

0.52

endpush

0.50

 ioutil

0.50

lichter

0.49

 localObject

0.47

didSet

0.46

 endforeach

0.45

CompilerServices

0.45

ettare

0.44

POSED

0.43

Activations Density 0.020%

terms related to the ease or difficulty of processes

No Comments

No Known Activations