INDEX

Explanations

words related to self-perception and reflection, especially in relation to appearance and choices

oai_token-act-pair · gemini-2.0-flash

mirror

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 reflection

-0.87

 reflecting

-0.86

 reflected

-0.84

 reflect

-0.82

 reflections

-0.80

reflect

-0.79

 Reflect

-0.78

 Reflection

-0.78

Reflect

-0.77

 reflects

-0.77

POSITIVE LOGITS

 referenties

0.78

 initComponents

0.66

BeginContext

0.59

 Paglinawan

0.58

gulier

0.58

 Theſe

0.57

 }}"></

0.56

 tận

0.56

machi

0.56

 Gallo

0.55

Activations Density 30.209%

words related to self-perception and reflection, especially in relation to appearance and choices

mirror

No Comments

No Known Activations