INDEX

Explanations

references to and descriptions of characters in stories

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

yg

-0.74

VERTIS

-0.72

sterdam

-0.69

gard

-0.68

rup

-0.68

IDA

-0.64

VEN

-0.63

ven

-0.63

yden

-0.62

LOCK

-0.62

POSITIVE LOGITS

acters

1.55

istically

1.38

istics

1.34

izations

1.06

isations

0.93

izes

0.90

 arcs

0.88

 assassination

0.87

 assassinate

0.86

 traits

0.84

Activations Density 0.620%

references to and descriptions of characters in stories

No Comments

No Known Activations