INDEX

Explanations

names of individuals and their associated affiliations or institutions

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

 дописавши

-0.85

 tartalomajánló

-0.74

MigrationBuilder

-0.64

DockStyle

-0.59

ranton

-0.59

Lähteet

-0.58

Pautan

-0.57

omock

-0.56

__":

-0.55

gypti

-0.54

POSITIVE LOGITS

 Gujarati

0.80

 Patel

0.76

 Ahmedabad

0.72

Gujarat

0.71

 Gujarat

0.71

ApiException

0.64

 Mota

0.58

aben

0.57

 Pare

0.54

PathVariable

0.53

Activations Density 0.068%

names of individuals and their associated affiliations or institutions

No Comments

No Known Activations