INDEX

Explanations

phrases and punctuation symbols within text, indicating a focus on sentence structure and syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 يتيمه

-0.67

zinha

-0.59

choenen

-0.55

гӀ

-0.53

Kariera

-0.53

ніципалі

-0.52

uttosto

-0.52

uremberg

-0.52

ising

-0.51

jercicio

-0.51

POSITIVE LOGITS

同上

0.91

ditto

0.74

こちらも

0.67

 ditto

0.64

同じく

0.59

 ebenfalls

0.59

FormTagHelper

0.57

 idem

0.56

 ibid

0.56

various

0.55

Activations Density 0.508%

phrases and punctuation symbols within text, indicating a focus on sentence structure and syntax

No Comments

No Known Activations