INDEX

Explanations

the word "time", and sometimes "heat"

oai_token-act-pair · gemini-2.0-flash

time

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<eos>

-0.94

-0.91

↵

-0.89

the

-0.84

↵↵

-0.82

-0.80

“

-0.77

-0.75

to

-0.74

POSITIVE LOGITS

Efq

1.70

 Monfieur

1.63

 Theſe

1.61

 Reſ

1.59

 myſelf

1.58

 iſt

1.49

 Anſ

1.46

 pleaſure

1.43

 Houſe

1.38

 Jefus

1.38

Activations Density 0.282%

the word "time", and sometimes "heat"

time

No Comments

No Known Activations