INDEX

Explanations

occurrences of the word "hit" or similar words relating to impact

oai_token-act-pair · gemini-2.0-flash

hit

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

-1.03

-1.00

-0.97

-0.96

↵↵

-0.96

<eos>

-0.93

-0.91

-0.87

-0.86

-0.83

POSITIVE LOGITS

Efq

1.76

 ―――――

1.59

 Theſe

1.55

 Majefty

1.54

 Monfieur

1.48

 itſelf

1.47

 Jefus

1.45

 auffi

1.42

 myſelf

1.42

 Anſ

1.41

Activations Density 3.429%

occurrences of the word "hit" or similar words relating to impact

hit

No Comments

No Known Activations