INDEX

Explanations

references to grant funding and research support

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

Efq

-0.83

 Jefus

-0.76

 ſeveral

-0.72

 Theſe

-0.72

 raiſ

-0.72

 themſelves

-0.71

 uſed

-0.70

 myſelf

-0.70

 diſt

-0.70

 reaſon

-0.69

POSITIVE LOGITS

 grants

0.87

 grant

0.86

 funding

0.85

funding

0.75

 funded

0.72

grants

0.70

funded

0.69

Grants

0.68

Funding

0.67

grant

0.67

Activations Density 0.324%

references to grant funding and research support

No Comments

No Known Activations