INDEX

Explanations

instances where the phrase "when it" is followed by a verb

oai_token-act-pair · gpt-3.5-turbo

instances of the pronoun "it" 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

 Dayton

-0.67

cox

-0.67

 Absent

-0.66

 Torn

-0.65

 Friend

-0.64

 Breast

-0.63

Orn

-0.62

 Electrical

-0.61

 Corpus

-0.61

 Socket

-0.59

POSITIVE LOGITS

alian

1.00

chy

0.99

asca

0.98

 happened

0.97

 mattered

0.93

 happens

0.92

unes

0.89

ueller

0.87

 transpired

0.86

 seems

0.86

Activations Density 0.262%

instances where the phrase "when it" is followed by a verb

instances of the pronoun "it" in various contexts

No Comments

No Known Activations