INDEX

Explanations

verbs that convey someone's opinion, thoughts, or actions

oai_token-act-pair · gemini-2.0-flash

offered

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

 emitted

-1.08

Efq

-1.01

XmlAccessType

-1.01

 raiſ

-0.97

 HasFactory

-0.97

 myſelf

-0.94

 collected

-0.92

PerformLayout

-0.90

obtained

-0.88

 becauſe

-0.88

POSITIVE LOGITS

<eos>

0.62

an

0.59

 losing

0.57

 offering

0.55

↵↵

0.53

 offers

0.53

↵

0.53

 seemed

0.52

 sending

0.52

Activations Density 1.794%

verbs that convey someone's opinion, thoughts, or actions

offered

No Comments

No Known Activations