INDEX

Explanations

verbs related to attributing actions or qualities to someone or something

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

rawdownloadcloneembedreportprint

-0.81

lite

-0.80

aspx

-0.70

ceans

-0.69

asp

-0.65

lake

-0.65

ENG

-0.63

oval

-0.60

bsp

-0.59

stall

-0.59

POSITIVE LOGITS

 blame

1.07

lled

0.81

 allegiance

0.79

 responsibility

0.76

ences

0.73

 charism

0.72

credit

0.72

 attribut

0.69

inished

0.69

 Attribution

0.68

Activations Density 0.025%

verbs related to attributing actions or qualities to someone or something

No Comments

No Known Activations