INDEX

Explanations

prepositions followed by a noun phrase

oai_token-act-pair · gpt-3.5-turbo

the word "of" and its frequency in various 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

 reperto

-0.80

ername

-0.70

 agre

-0.69

 destro

-0.68

fully

-0.65

respective

-0.63

anu

-0.62

BILL

-0.61

 preval

-0.60

 misunder

-0.60

POSITIVE LOGITS

icial

0.98

 sorts

0.96

 course

0.89

 Plenty

0.74

 Excellence

0.71

 Destruction

0.69

 Hearts

0.66

 Roses

0.65

 Lakes

0.64

 Spears

0.64

Activations Density 0.244%

prepositions followed by a noun phrase

the word "of" and its frequency in various contexts

No Comments

No Known Activations