INDEX

Explanations

words and phrases related to prominent public figures, particularly in the context of celebrities and political figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

its

-0.58

Its

-0.53

Its

-0.51

 stalo

-0.47

它是

-0.46

它的

-0.45

IntoConstraints

-0.45

 HasFactory

-0.43

its

-0.42

inhalt

-0.42

POSITIVE LOGITS

 himself

0.96

esque

0.86

 fans

0.82

 imperson

0.79

 Himself

0.76

himself

0.74

 haters

0.73

 admirers

0.73

fans

0.72

Зноскі

0.71

Activations Density 0.318%

words and phrases related to prominent public figures, particularly in the context of celebrities and political figures

No Comments

No Known Activations