INDEX

Explanations

references to the concept of restoration or returning to a previous state

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gom

-0.76

kers

-0.68

gerald

-0.66

kson

-0.63

fork

-0.62

rics

-0.62

atu

-0.62

onne

-0.61

agram

-0.61

ertodd

-0.61

POSITIVE LOGITS

 sanity

0.81

vig

0.79

 harmony

0.78

 restore

0.78

 composure

0.78

 restoration

0.75

 vitality

0.74

itial

0.74

 balance

0.74

 calm

0.73

Activations Density 0.014%

references to the concept of restoration or returning to a previous state

No Comments

No Known Activations