INDEX

Explanations

phrases that indicate denial or rejection of claims or arguments

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

GenerationType

-0.62

rscheinlichkeit

-0.49

GOTREF

-0.46

次代

-0.46

undes

-0.46

Архівовано

-0.44

specialchars

-0.42

LabelTagHelper

-0.42

 sayang

-0.42

WebElementEntity

-0.42

POSITIVE LOGITS

 skuto

0.74

 Truly

0.73

 affatto

0.72

 wirklich

0.71

Actual

0.71

 réellement

0.69

 tatsäch

0.69

Really

0.69

 whatsoever

0.68

Truly

0.67

Activations Density 0.429%

phrases that indicate denial or rejection of claims or arguments

No Comments

No Known Activations