INDEX

Explanations

negative words related to financial terms

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

 Norris

-0.71

 Burr

-0.70

 Arabian

-0.69

 Borders

-0.68

 Confederation

-0.67

Ell

-0.65

 Kern

-0.65

 Cree

-0.64

 square

-0.63

 Cotton

-0.63

POSITIVE LOGITS

based

1.59

related

1.47

driven

1.45

oriented

1.40

loving

1.39

laden

1.39

themed

1.37

filled

1.37

sized

1.34

induced

1.34

Activations Density 0.615%

negative words related to financial terms

No Comments

No Known Activations