INDEX

Explanations

words and phrases used in academic text, related to research, social science, and politics.

oai_token-act-pair · gemini-2.0-flash

within

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

GEBURTSDATUM

-1.12

 ComVisible

-0.83

webElementXpaths

-0.80

]--;

-0.74

oredCriteria

-0.71

 <<<<<<<<<<<<<<

-0.70

FailureListener

-0.70

 محفوظة

-0.70

 esternos

-0.69

 AssemblyProduct

-0.69

POSITIVE LOGITS

 within

0.73

within

0.66

 Within

0.59

Within

0.55

informed

0.52

 inform

0.47

 WITHIN

0.47

 informed

0.46

发表于

0.45

 informing

0.45

Activations Density 7.468%

words and phrases used in academic text, related to research, social science, and politics.

within

No Comments

No Known Activations