INDEX

Explanations

words related to aspects of writing, thinking, and argumentation

oai_token-act-pair · gemini-2.0-flash

speaking and speech

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

 beginnetje

-0.60

PhysRevD

-0.56

 ujednoznacz

-0.54

COUVER

-0.54

Rptr

-0.52

Identyfik

-0.52

Subview

-0.51

rawtypes

-0.50

ponses

-0.50

hindu

-0.49

POSITIVE LOGITS

 speaking

0.91

 spoken

0.88

 oral

0.84

 speech

0.81

 writing

0.77

 speak

0.74

speech

0.73

spoken

0.72

 parlando

0.71

 Speaking

0.71

Activations Density 1.712%

words related to aspects of writing, thinking, and argumentation

speaking and speech

No Comments

No Known Activations