INDEX

Explanations

references to specific geographical locations, particularly related to cities and suburbs

oai_token-act-pair · gpt-3.5-turbo

references to geographic locations and their contexts

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

ZI

-0.58

ructose

-0.55

 Pearce

-0.49

ramid

-0.48

zac

-0.47

ËĪ

-0.47

 Taste

-0.47

 Certain

-0.46

endez

-0.46

arget

-0.45

POSITIVE LOGITS

 disappears

0.70

 exists

0.69

has

0.69

 becomes

0.68

 underwent

0.67

 consists

0.66

 encompasses

0.66

 succeeded

0.66

 disappeared

0.65

 comprises

0.65

Activations Density 1.070%

references to specific geographical locations, particularly related to cities and suburbs

references to geographic locations and their contexts

No Comments

No Known Activations