INDEX

Explanations

links or relationships between different concepts or entities mentioned in the 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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

sburg

-0.77

Ħ¢

-0.77

perty

-0.72

issance

-0.67

XY

-0.66

 Nights

-0.65

 outnumbered

-0.64

ORK

-0.63

 Liberties

-0.60

cheat

-0.60

POSITIVE LOGITS

 knot

1.03

edin

1.02

 connecting

0.91

later

0.90

 dots

0.89

 link

0.87

 linking

0.84

link

0.82

 links

0.82

links

0.82

Activations Density 0.901%

links or relationships between different concepts or entities mentioned in the text

No Comments

No Known Activations