INDEX

Explanations

terms related to reflection and self-assessment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

paravant

-0.82

робнее

-0.77

OPSIS

-0.74

 Normdatei

-0.70

 coisa

-0.69

dtd

-0.69

 Emma

-0.68

osene

-0.67

 brancas

-0.66

 FishBase

-0.66

POSITIVE LOGITS

 reflected

1.61

 reflections

1.54

 reflecting

1.53

 reflect

1.50

 reflection

1.50

 reflects

1.50

 refle

1.49

 Reflect

1.48

 Reflection

1.43

reflect

1.40

Activations Density 0.068%

terms related to reflection and self-assessment

No Comments

No Known Activations