INDEX

Explanations

words related to political figures and events

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

KB

-0.88

çİĭ

-0.79

MB

-0.79

ç¥ŀ

-0.78

AGES

-0.74

-0.72

-0.71

 Gear

-0.70

 Bohem

-0.70

-0.69

POSITIVE LOGITS

re

1.36

rez

1.12

RE

1.12

reb

1.10

arre

0.99

rey

0.98

reys

0.97

Ã¨re

0.97

rem

0.96

res

0.93

Activations Density 0.134%

words related to political figures and events

No Comments

No Known Activations