INDEX

Explanations

phrases indicating participation or engagement in activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

-0.72

-0.69

く

-0.69

ers

-0.66

 Brito

-0.65

 sodass

-0.65

GOTREF

-0.62

 dass

-0.62

ony

-0.61

ec

-0.61

POSITIVE LOGITS

 involved

1.87

 Involved

1.86

involved

1.77

 involve

1.75

 INVOLVED

1.62

 involves

1.60

 involvement

1.60

 Involvement

1.57

 INVOL

1.54

 involving

1.52

Activations Density 0.074%

phrases indicating participation or engagement in activities

No Comments

No Known Activations

phrases indicating participation or engagement in activities

No Comments

No Known Activations