INDEX

Explanations

transition words and phrases indicative of reasoning

oai_token-act-pair · gemini-2.0-flash

words with specific formatting or styles

np_token-act-pair-logits · gpt-4o-mini

Say "for this reason"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 nakalista

-0.96

enumi

-0.93

 AspNetCore

-0.90

 resourceCulture

-0.90

NameInMap

-0.88

Билгалдахарш

-0.87

 autorytatywna

-0.86

 propOrder

-0.85

 Wikimedijinoj

-0.84

 AssemblyProduct

-0.83

POSITIVE LOGITS

 مواليد

0.59

 poffible

0.58

 becauſe

0.57

 ſeveral

0.54

 ſhe

0.54

 Theſe

0.51

 againſt

0.50

 ſhall

0.48

 sauvages

0.48

 fufficient

0.47

Activations Density 6.392%

transition words and phrases indicative of reasoning

words with specific formatting or styles

Say "for this reason"

No Comments

No Known Activations