INDEX

Explanations

conjunctions and coordinating phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RectangleBorder

-0.47

 klap

-0.46

 leger

-0.46

fes

-0.45

}}},

-0.45

 call

-0.45

Dul

-0.45

Call

-0.45

 code

-0.45

POSITIVE LOGITS

 avoient

0.86

 Paglinawan

0.85

LookAnd

0.82

 étoient

0.82

 auroit

0.82

 feroit

0.77

 ſever

0.77

 AssemblyCompany

0.77

GHIJKLM

0.77

RRect

0.73

Activations Density 0.430%

conjunctions and coordinating phrases

No Comments

No Known Activations