INDEX

Explanations

terms and concepts related to mathematical properties and structures, particularly in relation to positive and real values in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BeginContext

-0.70

InSection

-0.53

 VIAF

-0.52

 kaynağından

-0.51

 Вікіпе

-0.49

getMenuInflater

-0.46

ActionMode

-0.45

\{\\

-0.45

spender

-0.45

новништво

-0.44

POSITIVE LOGITS

 Sociales

0.74

 '\\;'

0.73

mitian

0.72

رشف

0.70

 convex

0.70

 concave

0.69

 virginity

0.69

')));

0.68

mpotent

0.66

 vegetarian

0.66

Activations Density 1.730%

terms and concepts related to mathematical properties and structures, particularly in relation to positive and real values in various contexts

No Comments

No Known Activations