INDEX

Explanations

phrases related to a continuous process or progression

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

than

-0.78

INT

-0.76

anth

-0.75

obal

-0.75

ubi

-0.75

ORS

-0.74

jon

-0.74

MIN

-0.73

dor

-0.73

gart

-0.72

POSITIVE LOGITS

 transsexual

0.77

 alike

0.72

 metab

0.70

 depending

0.69

fac

0.68

 stamped

0.68

 correspondence

0.67

 throughout

0.66

 basis

0.65

 across

0.64

Activations Density 0.454%

phrases related to a continuous process or progression

No Comments

No Known Activations