INDEX

Explanations

phrases related to the effects of various actions, events, or substances

oai_token-act-pair · gpt-3.5-turbo

references to the impact or effect of various factors on subjects or situations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.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

SourceFile

-0.81

©¶æ¥µ

-0.73

Intel

-0.72

DragonMagazine

-0.70

aniel

-0.67

wine

-0.67

Plex

-0.67

NB

-0.67

olf

-0.65

POSITIVE LOGITS

erous

1.20

 behalf

1.10

roads

0.80

 impact

0.80

 digestion

0.78

shore

0.77

impact

0.77

 impacting

0.75

 shaping

0.73

etime

0.73

Activations Density 0.068%

phrases related to the effects of various actions, events, or substances

references to the impact or effect of various factors on subjects or situations

No Comments

No Known Activations