INDEX

Explanations

phrases related to appearances or occurrences

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

shaw

-0.85

EStreamFrame

-0.75

cise

-0.73

dp

-0.72

current

-0.67

yright

-0.66

ses

-0.65

Ã§a

-0.64

imar

-0.63

ilit

-0.63

POSITIVE LOGITS

 prominently

0.82

 onstage

0.69

 alongside

0.65

 victorious

0.64

ãĤ¤ãĥĪ

0.64

ead

0.64

æ³

0.63

antly

0.63

éĹ

0.61

 spor

0.61

Activations Density 0.540%

phrases related to appearances or occurrences

No Comments

No Known Activations