INDEX

Explanations

terms related to political leadership, specifically the presidency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Roskov

-0.84

oog

-0.74

 Turin

-0.72

 Borgo

-0.67

'</

-0.66

ỡng

-0.66

jerg

-0.66

 Turi

-0.65

Jau

-0.65

ske

-0.64

POSITIVE LOGITS

 Presidents

1.28

 presidents

1.20

Presidents

1.13

 President

1.12

 president

1.03

 presidential

1.00

 PRESIDENT

0.96

 Presidential

0.94

 Präsident

0.91

 presidency

0.90

Activations Density 0.071%

terms related to political leadership, specifically the presidency

No Comments

No Known Activations