INDEX

Explanations

words related to agreements or disagreements in opinions or statements

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

oufl

-0.77

 typh

-0.76

asus

-0.73

agin

-0.71

 Tycoon

-0.70

ogo

-0.67

 glands

-0.67

crow

-0.66

aval

-0.66

 earthqu

-0.66

POSITIVE LOGITS

 unanimously

0.98

 agreement

0.81

 thereto

0.79

rences

0.76

lihood

0.75

 agreeing

0.74

ably

0.74

 agrees

0.73

SOURCE

0.73

upon

0.69

Activations Density 0.699%

words related to agreements or disagreements in opinions or statements

No Comments

No Known Activations