INDEX

Explanations

instances of labeling or reference tags

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

Читайте

-0.65

"]));

-0.60

KommentareTeilen

-0.59

parsedMessage

-0.57

ibid

-0.51

 Stande

-0.51

 />";

-0.51

")));

-0.50

wnież

-0.50

")));

-0.49

POSITIVE LOGITS

 labels

1.02

 Labels

0.99

labels

0.97

 label

0.90

lbl

0.89

 LABEL

0.88

LabelTagHelper

0.85

tichetta

0.85

 Label

0.85

Labels

0.82

Activations Density 0.081%

instances of labeling or reference tags

No Comments

No Known Activations