INDEX

Explanations

phrases related to persistence or strong beliefs in a context

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

dm

-0.82

ahime

-0.77

aye

-0.76

externalActionCode

-0.72

alf

-0.71

yet

-0.71

DF

-0.69

heimer

-0.68

åĤ

-0.67

AAF

-0.65

POSITIVE LOGITS

 dreamed

0.90

 fascinated

0.87

 strive

0.87

theless

0.85

 lurking

0.81

 wondered

0.78

 underestimated

0.77

 appreciated

0.77

 striving

0.75

 welcome

0.75

Activations Density 0.396%

phrases related to persistence or strong beliefs in a context

No Comments

No Known Activations