INDEX

Explanations

references to grading or educational performance

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.59

closePath

-0.63

ManyToMany

-0.61

Cyfeiriadau

-0.57

 насеље

-0.56

مصادر

-0.55

OneToMany

-0.55

Alemania

-0.52

set

-0.52

 nawr

-0.52

POSITIVE LOGITS

 maneu

1.33

 grade

1.25

 accla

1.24

Juf

1.23

 GRADE

1.21

 Khart

1.18

 Grades

1.17

 Grade

1.17

 Minang

1.17

 riviera

1.16

Activations Density 0.038%

references to grading or educational performance

No Comments

No Known Activations