INDEX

Explanations

statements indicating meaning or implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 sight

-0.57

-0.55

hä

-0.46

ub

-0.46

Kob

-0.46

Cordialement

-0.45

自行

-0.44

py

-0.43

 trends

-0.43

ynomial

-0.42

POSITIVE LOGITS

 مرئيه

1.09

 للاسماء

0.96

 MEANS

0.93

意味着

0.92

 means

0.91

évaluateur

0.88

DockStyle

0.88

 Means

0.85

 artinya

0.83

 gynhyrchwyd

0.83

Activations Density 0.210%

statements indicating meaning or implications

No Comments

No Known Activations