INDEX

Explanations

words like "essentially" and occurrences of the word "inside," which usually suggest a description or discussion of something contained within a space or system.

oai_token-act-pair · gemini-2.0-flash

inside, essentially

np_max-act · gemini-2.0-flash

say "the"

np_max-act-logits · gpt-5-mini Triggered by @chenshw0109

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

the

-1.02

-0.92

-0.91

-0.88

-0.86

-0.85

De

-0.85

POSITIVE LOGITS

Efq

1.43

 Theſe

1.41

 ainfi

1.39

 ſtate

1.34

 auffi

1.29

 auroit

1.29

 purpoſe

1.25

 feroit

1.24

 avoient

1.23

 fubject

1.21

Activations Density 2.570%

words like "essentially" and occurrences of the word "inside," which usually suggest a description or discussion of something contained within a space or system.

inside, essentially

say "the"

No Comments

No Known Activations

words like "essentially" and occurrences of the word "inside," which usually suggest a description or discussion of something contained within a space or system.

inside, essentially

say "the"

No Comments

No Known Activations