INDEX

Explanations

statements related to acceptance or approval

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

phabet

-0.76

APH

-0.75

Ranked

-0.72

ammy

-0.72

########

-0.71

loo

-0.70

 Tycoon

-0.69

urst

-0.69

eways

-0.69

obiles

-0.68

POSITIVE LOGITS

 accepting

0.99

ably

0.90

 accept

0.88

 accepts

0.84

 admit

0.81

 acceptance

0.81

 uncond

0.79

 admitting

0.78

 willingly

0.77

 defeat

0.75

Activations Density 2.151%

statements related to acceptance or approval

No Comments

No Known Activations