INDEX

Explanations

hyphenated words containing "self" or "co" to indicate some kind of interaction or relationship

oai_token-act-pair · gemini-2.0-flash

-

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-1.28

-0.82

-0.74

-0.64

-0.61

-0.60

-0.57

-0.56

-0.55

POSITIVE LOGITS

 itſelf

1.24

 myſelf

0.94

ſelf

0.93

StoryboardSegue

0.93

ſelves

0.92

 ་་

0.92

 pleaſure

0.90

 raiſ

0.90

']))

0.86

 Anſ

0.85

Activations Density 2.178%

hyphenated words containing "self" or "co" to indicate some kind of interaction or relationship

-

No Comments

No Known Activations