INDEX

Explanations

verbs related to possibility or expectation

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

imo

-0.62

ricular

-0.60

tein

-0.59

Owner

-0.58

 Archer

-0.57

usive

-0.57

tek

-0.57

me

-0.57

 Owner

-0.57

 vein

-0.57

POSITIVE LOGITS

 ourselves

1.31

 collectively

0.88

 presume

0.86

blogs

0.83

 electing

0.77

 incarcer

0.76

 glimpse

0.73

 infer

0.73

 mortals

0.72

ury

0.72

Activations Density 0.386%

verbs related to possibility or expectation

No Comments

No Known Activations