INDEX

Explanations

words and phrases indicating that something exists, is permitted, or has happened.

oai_token-act-pair · gemini-2.0-flash

have

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

HAVE

-1.00

gets

-0.96

gives

-0.93

sells

-0.93

worked

-0.92

tells

-0.91

knew

-0.91

performs

-0.89

shall

-0.89

adds

-0.88

POSITIVE LOGITS

 never

0.86

put

0.82

 have

0.82

 make

0.74

 need

0.73

 always

0.73

 also

0.72

esgue

0.71

 take

0.71

do

0.70

Activations Density 5.283%

words and phrases indicating that something exists, is permitted, or has happened.

have

No Comments

No Known Activations