INDEX

Explanations

terms related to the death penalty

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

pexpr

-0.63

dits

-0.61

cheme

-0.57

']").

-0.57

 baseman

-0.55

lgari

-0.54

ǔ

-0.53

]").

-0.53

 Assignee

-0.52

бираем

-0.52

POSITIVE LOGITS

 death

3.98

death

3.56

 Death

3.55

 DEATH

3.42

Death

3.40

DEATH

3.03

 deaths

2.79

 muerte

2.58

 Deaths

2.55

 morte

2.38

Activations Density 0.112%

terms related to the death penalty

No Comments

No Known Activations