INDEX

Explanations

phrases related to mixing or combining different elements

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

holes

-0.75

den

-0.71

ond

-0.71

writers

-0.69

gun

-0.68

 Passage

-0.67

sburg

-0.67

}}

-0.66

ACH

-0.65

otle

-0.65

POSITIVE LOGITS

 sexes

1.08

 disparate

0.93

 seamlessly

0.91

 together

0.89

 oppos

0.89

 between

0.85

 genders

0.83

 genres

0.81

 conflicting

0.79

 Between

0.75

Activations Density 0.884%

phrases related to mixing or combining different elements

No Comments

No Known Activations