INDEX

Explanations

proper nouns, particularly names of individuals

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

 itſelf

-1.01

 pleaſure

-0.94

 ſmall

-0.90

 myſelf

-0.87

 Anſ

-0.83

 ſeveral

-0.81

 Conſ

-0.80

 Reſ

-0.80

 Diſ

-0.79

 Monfieur

-0.78

POSITIVE LOGITS

 Edward

0.76

 George

0.74

 Charles

0.74

djangoproject

0.72

 James

0.70

("%.

0.70

 Robert

0.69

 Henry

0.69

 getopt

0.67

aarrggbb

0.67

Activations Density 0.898%

proper nouns, particularly names of individuals

No Comments

No Known Activations