INDEX

Explanations

terms related to the field of prosthetics and prosthetic limbs

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

INESS

-0.82

hound

-0.76

hower

-0.74

hare

-0.67

Magikarp

-0.67

é¾į

-0.67

ãĥ¯ãĥ³

-0.66

ÃĽ

-0.66

WT

-0.64

Roe

-0.63

POSITIVE LOGITS

hetics

1.23

hetic

1.16

 prost

1.11

 amput

1.09

hesis

1.00

heses

0.98

orius

0.95

ificial

0.88

 limbs

0.83

 limb

0.77

Activations Density 0.028%

terms related to the field of prosthetics and prosthetic limbs

No Comments

No Known Activations