INDEX

Explanations

terms related to political ideologies and their critiques

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

-0.80

wdata

-0.69

 abiti

-0.66

laşı

-0.62

caption

-0.60

Kla

-0.59

 Fletcher

-0.59

ț

-0.58

 lotes

-0.58

Kla

-0.58

POSITIVE LOGITS

 itſelf

0.95

 myſelf

0.94

Efq

0.88

 '\\;'

0.85

 becauſe

0.84

 BoxDecoration

0.83

 leaſt

0.83

cist

0.83

 depositphotos

0.83

izm

0.82

Activations Density 0.143%

terms related to political ideologies and their critiques

No Comments

No Known Activations