INDEX

Explanations

phrases indicating justification or explanation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 الحره

-0.90

 समीक्षक

-0.90

edipus

-0.84

}$

-0.83

 dalamnya

-0.81

extAlignment

-0.80

orgeous

-0.80

 Schulte

-0.80

 câte

-0.79

IsPostBack

-0.79

POSITIVE LOGITS

 reasons

2.14

 reason

2.13

 Reason

1.93

 Reasons

1.92

 REASON

1.90

reason

1.86

reasons

1.85

Reason

1.84

Reasons

1.75

 REASONS

1.72

Activations Density 0.107%

phrases indicating justification or explanation

No Comments

No Known Activations