INDEX

Explanations

phrases referring to causes or explanations

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

extAlignment

-0.98

orgeous

-0.96

 الحره

-0.94

BeginContext

-0.88

Datuak

-0.87

Atsauces

-0.86

 كومونز

-0.86

haustible

-0.85

edipus

-0.85

zsef

-0.84

POSITIVE LOGITS

 reasons

1.65

 Reasons

1.47

 reason

1.45

 Reason

1.43

 REASON

1.39

reasons

1.39

Reason

1.30

Reasons

1.27

 REASONS

1.25

reason

1.25

Activations Density 0.083%

phrases referring to causes or explanations

No Comments

No Known Activations