INDEX

Explanations

text that contains the word "fine" or "unfortunately" in the context of programming or technical issues

oai_token-act-pair · gemini-2.0-flash

fine

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

 myſelf

-1.67

 Monfieur

-1.59

Efq

-1.50

 Jefus

-1.46

 itſelf

-1.45

 avoient

-1.40

 themſelves

-1.38

 himſelf

-1.38

 feroit

-1.37

 Majefty

-1.32

POSITIVE LOGITS

<eos>

0.90

↵

0.90

0.88

</code>

0.85

ism

0.84

ary

0.82

er

0.79

0.77

</i>

0.76

Activations Density 1.467%

text that contains the word "fine" or "unfortunately" in the context of programming or technical issues

fine

No Comments

No Known Activations