INDEX

Explanations

descriptions related to physical locations or scenery

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

np

-0.66

{"

-0.66

ugal

-0.63

aho

-0.60

AAA

-0.59

acan

-0.58

 Alright

-0.58

kind

-0.58

romeda

-0.58

sson

-0.57

POSITIVE LOGITS

 even

0.81

 practically

0.80

 barely

0.77

ruciating

0.76

 unus

0.73

 almost

0.73

 warrant

0.73

 bordering

0.72

 scarcely

0.70

 hardly

0.70

Activations Density 1.101%

descriptions related to physical locations or scenery

No Comments

No Known Activations