INDEX

Explanations

references to the term "mid."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

 kaynağından

-0.70

\}\\

-0.60

yntaxException

-0.60

HostException

-0.57

fmt

-0.56

FTFY

-0.55

 Thesaurus

-0.53

 foramen

-0.53

MessageOf

-0.53

ecake

-0.53

POSITIVE LOGITS

mid

0.85

MID

0.76

dling

0.75

dles

0.75

Mid

0.74

Mid

0.73

dler

0.71

 mids

0.71

dled

0.66

range

0.64

Activations Density 0.071%

references to the term "mid."

No Comments

No Known Activations