INDEX

Explanations

negative contractions that indicate denial or disagreement

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

věř

-0.65

ieszcz

-0.62

 sexta

-0.62

ing

-0.62

wł

-0.61

Swift

-0.60

 Swain

-0.58

 Bande

-0.57

 sebelumnya

-0.57

reif

-0.56

POSITIVE LOGITS

do

0.94

новништво

0.94

erover

0.90

evos

0.88

DO

0.87

 does

0.85

 Moulton

0.85

 have

0.84

 سكانية

0.84

 Does

0.84

Activations Density 0.135%

negative contractions that indicate denial or disagreement

No Comments

No Known Activations