INDEX

Explanations

discussions around contradictions and contrasts in statements

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

ficulty

-0.63

AutoScale

-0.61

انجليز

-0.60

 Савезне

-0.58

quels

-0.56

StoryboardSegue

-0.55

nesse

-0.53

[];

-0.53

mergeFrom

-0.53

 mergeFrom

-0.52

POSITIVE LOGITS

 though

0.73

 anyway

0.70

 especially

0.69

but

0.63

 frankly

0.61

 Tuttavia

0.60

huh

0.60

enumi

0.59

especially

0.59

tbh

0.58

Activations Density 0.291%

discussions around contradictions and contrasts in statements

No Comments

No Known Activations