INDEX

Explanations

expressions of encouragement and support for actions or behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

id

-0.76

lands

-0.75

("")]

-0.75

ber

-0.65

as

-0.63

}{|

-0.63

off

-0.62

io

-0.62

queline

-0.62

land

-0.61

POSITIVE LOGITS

 encouraged

2.04

 encourage

2.01

 encourages

2.00

 Encourage

1.97

 encouragement

1.92

Encourage

1.87

couraged

1.82

 encouraging

1.74

couraging

1.73

encouragement

1.73

Activations Density 0.096%

expressions of encouragement and support for actions or behaviors

No Comments

No Known Activations