INDEX

Explanations

phrases containing the word "like" followed by a comparison or analogy

oai_token-act-pair · gpt-3.5-turbo

references to comparisons and contrasts involving the word "like."

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

rid

-0.72

Ł

-0.71

¬¼

-0.69

ivia

-0.67

obal

-0.64

enter

-0.63

vation

-0.61

oval

-0.60

afety

-0.60

jam

-0.60

POSITIVE LOGITS

 livest

0.69

 though

0.66

 wherein

0.65

 except

0.65

ingers

0.64

Downloadha

0.61

 however

0.61

whose

0.59

 Flavoring

0.59

Activations Density 0.253%

phrases containing the word "like" followed by a comparison or analogy

references to comparisons and contrasts involving the word "like."

No Comments

No Known Activations