INDEX

Explanations

words and phrases that express negative feelings, disapproval, or unethical behavior

oai_token-act-pair · gemini-2.0-flash

negative sentiment

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.49

dr

-0.47

pex

-0.46

La

-0.46

dev

-0.44

Ber

-0.44

↵↵

-0.44

Int

-0.44

POSITIVE LOGITS

 itſelf

0.90

 Majefty

0.88

 pleaſure

0.83

 Monfieur

0.81

 Jefus

0.80

 ―――――

0.78

 fubject

0.78

 ſever

0.78

RenderAtEndOf

0.78

 doubtnut

0.77

Activations Density 2.317%

words and phrases that express negative feelings, disapproval, or unethical behavior

negative sentiment

No Comments

No Known Activations