INDEX

Explanations

sentences that express opinions or evaluations about experiences, specifically in reviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 للمعارف

-0.72

 nakalista

-0.62

ranslated

-0.59

########.

-0.57

UnusedPrivate

-0.57

BeginContext

-0.55

 متعلقه

-0.51

principalTable

-0.51

 infatti

-0.51

ulasi

-0.50

POSITIVE LOGITS

 moderately

0.67

 slightly

0.67

slightly

0.64

 mildly

0.64

 disambiguazione

0.63

Decent

0.62

meh

0.60

overall

0.57

 decent

0.56

 непло

0.56

Activations Density 0.181%

sentences that express opinions or evaluations about experiences, specifically in reviews

No Comments

No Known Activations