INDEX

Explanations

political assertions related to investigations or claims of wrongdoing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 cherchés

-0.59

 pilota

-0.59

PerformLayout

-0.55

nissen

-0.53

ordat

-0.50

EndInit

-0.50

 kilometres

-0.49

पया

-0.49

cillors

-0.47

loten

-0.47

POSITIVE LOGITS

 Trump

1.08

Trump

1.01

 impeachment

0.92

 presidential

0.89

 impea

0.76

 Biden

0.76

 America

0.75

 Presidential

0.75

 President

0.72

 congressional

0.72

Activations Density 0.689%

political assertions related to investigations or claims of wrongdoing

No Comments

No Known Activations