INDEX

Explanations

uses of the words "seem" or "like"

oai_token-act-pair · gemini-2.0-flash

like

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

entary

-0.49

Lab

-0.49

perate

-0.47

 ""),

-0.47

okan

-0.47

днако

-0.46

 déb

-0.46

 тока

-0.45

efits

-0.45

</strong>

-0.45

POSITIVE LOGITS

-------------</

0.90

AddTagHelper

0.76

 lenker

0.76

 Wicidata

0.76

 MainAxisSize

0.74

----</

0.72

Personendaten

0.71

 AppModule

0.70

 tfsi

0.69

хьтан

0.69

Activations Density 1.546%

uses of the words "seem" or "like"

like

No Comments

No Known Activations