INDEX

Explanations

quantitative data and numeric performance metrics related to specific subjects or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 ddelweddau

-0.54

parsedMessage

-0.49

AndEndTag

-0.49

 elettrico

-0.49

每

-0.49

iramente

-0.48

principalColumn

-0.47

κρα

-0.47

nost

-0.46

 tùy

-0.46

POSITIVE LOGITS

 total

0.73

 collectively

0.70

total

0.64

 totaling

0.63

 totalling

0.62

合わせて

0.62

計

0.61

 cumul

0.61

 totale

0.60

合計

0.59

Activations Density 0.304%

quantitative data and numeric performance metrics related to specific subjects or groups

No Comments

No Known Activations