INDEX

Explanations

identifiers and attributes related to user and product data structures

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

-1.17

-0.95

-0.93

-0.92

-0.91

-0.90

-0.89

POSITIVE LOGITS

 myſelf

2.22

 themſelves

2.03

 purpoſe

2.03

 himſelf

1.97

 itſelf

1.96

ſelf

1.92

 Theſe

1.90

ſelves

1.88

 raiſ

1.83

 ſtate

1.82

Activations Density 0.256%

identifiers and attributes related to user and product data structures

No Comments

No Known Activations