INDEX

Explanations

references to names and affiliations in academic contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 كومونز

-0.79

 AssemblyCulture

-0.71

Personendaten

-0.66

MLLoader

-0.66

 HasFactory

-0.66

ſelf

-0.65

 Majefty

-0.62

 وتسجيلات

-0.60

الحياه

-0.59

intios

-0.59

POSITIVE LOGITS

Yu

0.79

Yu

0.72

0.66

Ye

0.66

Ye

0.65

Ya

0.58

Ya

0.57

 يتيمه

0.56

Activations Density 0.149%

references to names and affiliations in academic contexts

No Comments

No Known Activations