INDEX

Explanations

mentions of 'the' in specific contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 accordingly

-0.76

 furthermore

-0.76

merce

-0.76

 anew

-0.74

Layer

-0.71

olicy

-0.69

ocument

-0.66

ooth

-0.66

 nevertheless

-0.65

Versions

-0.63

POSITIVE LOGITS

 outset

1.25

 aforementioned

1.16

 standpoint

1.13

 same

1.05

 confines

0.99

 depths

0.98

 earliest

0.93

 foregoing

0.89

 beginnings

0.89

 usual

0.89

Activations Density 0.198%

mentions of 'the' in specific contexts

occurrences of the word "the"

No Comments

No Known Activations