INDEX

Explanations

mentions of blog posts or articles within a text

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

estial

-0.75

 Orchestra

-0.72

 Flavoring

-0.71

 leukemia

-0.66

ãĤ¤ãĥĪ

-0.65

STON

-0.65

owship

-0.62

 Brill

-0.62

ye

-0.61

 bands

-0.60

POSITIVE LOGITS

mortem

1.31

gres

1.31

doctoral

1.14

hum

1.10

mort

1.04

natal

1.01

greSQL

1.01

doc

0.99

modern

0.95

orial

0.94

Activations Density 0.036%

mentions of blog posts or articles within a text

No Comments

No Known Activations