INDEX

Explanations

phrases related to secrets and hidden information

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

annis

-0.79

ulf

-0.77

gaard

-0.76

odcast

-0.74

lihood

-0.73

kins

-0.73

FG

-0.72

Kay

-0.70

adjusted

-0.70

©¶æ

-0.70

POSITIVE LOGITS

ariat

1.33

arial

1.23

 stash

0.88

rets

0.87

 ingredient

0.86

 sauce

0.85

 recess

0.81

 hatch

0.81

 handshake

0.79

 ballot

0.78

Activations Density 0.267%

phrases related to secrets and hidden information

No Comments

No Known Activations