INDEX

Explanations

emotional reactions

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

tein

-0.65

Ranked

-0.61

AMA

-0.60

hem

-0.59

 Merge

-0.58

 dated

-0.57

inances

-0.56

ILA

-0.56

ramid

-0.56

oba

-0.55

POSITIVE LOGITS

 aback

0.90

 enough

0.82

dy

0.77

ragon

0.76

 seeing

0.73

NESS

0.71

quartered

0.70

 hearing

0.69

icative

0.68

 about

0.68

Activations Density 0.789%

emotional reactions

No Comments

No Known Activations