INDEX

Explanations

concepts and ideas related to potential issues or features

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

uild

-0.63

NetMessage

-0.61

onics

-0.61

hell

-0.60

vironments

-0.60

onz

-0.60

eric

-0.59

riages

-0.58

lems

-0.58

 TAMADRA

-0.57

POSITIVE LOGITS

 overlooked

0.87

 limitation

0.80

 notable

0.79

 involves

0.79

 relates

0.76

 pecul

0.74

 noteworthy

0.72

 distinguishing

0.71

 compl

0.71

 difference

0.69

Activations Density 0.064%

concepts and ideas related to potential issues or features

No Comments

No Known Activations