INDEX

Explanations

words/phrases indicating evaluation of a situation

oai_token-act-pair · gemini-2.0-flash

problems or issues

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

abetes

-0.77

StateList

-0.54

 Baillargeon

-0.49

=$

-0.49

idosis

-0.49

unched

-0.49

rceil

-0.48

$/

-0.48

тет

-0.48

 tene

-0.48

POSITIVE LOGITS

<bos>

1.79

 itſelf

0.86

 himſelf

0.84

 Theſe

0.75

 comigo

0.74

ſelf

0.74

 themſelves

0.73

 pleaſure

0.73

 Houſe

0.72

 Jefus

0.71

Activations Density 2.276%

words/phrases indicating evaluation of a situation

problems or issues

No Comments

No Known Activations