INDEX

Explanations

phrases related to significant events or key moments in a narrative

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inately

-0.85

ancies

-0.81

ateurs

-0.73

qus

-0.71

tails

-0.67

lying

-0.65

flat

-0.65

ulia

-0.65

 cabinets

-0.64

enhagen

-0.64

POSITIVE LOGITS

 milestone

0.88

 epoch

0.81

 anniversary

0.79

atform

0.78

 moment

0.76

iphany

0.73

 unfolding

0.72

 breakthrough

0.72

ARK

0.72

 event

0.72

Activations Density 0.189%

phrases related to significant events or key moments in a narrative

No Comments

No Known Activations