INDEX

Explanations

the word "forest"

oai_token-act-pair · gemini-2.0-flash

forest

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

<bos>

-0.77

is

-0.76

-0.72

<eos>

-0.71

-0.70

-0.69

-0.68

-0.67

-0.66

POSITIVE LOGITS

 Monfieur

1.09

 Houſe

0.98

 ་་

0.94

 myſelf

0.94

Efq

0.92

 houſe

0.92

 itſelf

0.90

 Reſ

0.89

 InputDecoration

0.88

 ſever

0.87

Activations Density 1.344%

the word "forest"

forest

No Comments

No Known Activations