INDEX

Explanations

phrases indicating conclusions or deductions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Pyx

-0.55

HasForeignKey

-0.52

 muualla

-0.50

PerformLayout

-0.50

 Wiktionnaire

-0.47

 الحره

-0.47

 Soro

-0.47

principalColumn

-0.46

.$,

-0.45

 costing

-0.44

POSITIVE LOGITS

 obtains

0.68

 obtain

0.68

 need

0.62

 بيها

0.59

 should

0.58

 must

0.57

 obtained

0.54

arschu

0.53

 want

0.53

 Mexique

0.50

Activations Density 0.509%

phrases indicating conclusions or deductions

No Comments

No Known Activations