INDEX

Explanations

phrases related to creating or establishing something

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

phia

-0.71

duty

-0.71

say

-0.69

EGA

-0.67

ni

-0.66

 WATCHED

-0.63

imation

-0.63

words

-0.59

pling

-0.59

gnu

-0.58

POSITIVE LOGITS

 havoc

0.98

 anew

0.81

å¥³

0.76

unique

0.74

ãĥ¼ãĥĨãĤ£

0.74

ãĥĩãĤ£

0.74

idable

0.74

ilts

0.71

 hybrids

0.71

Space

0.70

Activations Density 0.654%

phrases related to creating or establishing something

No Comments

No Known Activations