INDEX

Explanations

phrases which contain the word "hit" and indicate success or achieving a goal.

oai_token-act-pair · gemini-2.0-flash

hit

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 CreateTagHelper

-0.69

 virginity

-0.65

 giustizia

-0.60

 équilibr

-0.58

 BoxDecoration

-0.57

httphttps

-0.55

 lievito

-0.55

fitriones

-0.55

 intégrée

-0.53

 placée

-0.52

POSITIVE LOGITS

 EconPapers

0.51

alco

0.51

 DataLoader

0.49

 policy

0.49

policy

0.47

 estekak

0.47

órmula

0.47

leda

0.46

HandlerContext

0.45

 interest

0.45

Activations Density 8.192%

phrases which contain the word "hit" and indicate success or achieving a goal.

hit

No Comments

No Known Activations