INDEX

Explanations

statements about opinions, assertions, and disclaimers regarding information and its accuracy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

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

SaveChangesAsync

-0.72

 ujednoznacz

-0.63

发表于

-0.60

 estimés

-0.59

ništ

-0.56

ECTOS

-0.54

CommandText

-0.54

ateness

-0.53

fillType

-0.53

 somehow

-0.52

POSITIVE LOGITS

 subject

0.66

subject

0.55

SourceChecksum

0.54

 soggetto

0.52

chmal

0.52

niczy

0.51

 cumulative

0.50

 strictly

0.50

 hereinafter

0.49

 SUBJECT

0.49

Activations Density 0.380%

statements about opinions, assertions, and disclaimers regarding information and its accuracy

No Comments

No Known Activations