INDEX

Explanations

phrases related to time

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

atform

-0.79

heses

-0.78

istani

-0.76

roma

-0.76

obal

-0.74

amara

-0.74

ivist

-0.72

iege

-0.70

vertisement

-0.69

SpaceEngineers

-0.68

POSITIVE LOGITS

ously

0.87

ographed

0.82

lled

0.77

lla

0.76

eer

0.69

lda

0.68

ira

0.67

mons

0.66

hower

0.66

Activations Density 0.023%

phrases related to time

No Comments

No Known Activations