INDEX

Explanations

references to individuals and their perceived failures or denials 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

the

-0.79

-0.70

 this

-0.57

 these

-0.52

 about

-0.51

an

-0.51

 that

-0.49

-0.48

 inventory

-0.48

 there

-0.47

POSITIVE LOGITS

parsedMessage

0.94

Билгалдахарш

0.85

WebVitals

0.84

tvguidetime

0.80

SequentialGroup

0.78

 himo

0.78

 noqa

0.76

typeorm

0.76

 okuyayım

0.76

ViewFeatures

0.75

Activations Density 0.277%

references to individuals and their perceived failures or denials in various contexts

No Comments

No Known Activations