INDEX

Explanations

instances of the word "both" in sentences comparing two entities or ideas

oai_token-act-pair · gpt-3.5-turbo

references to contrasting elements or pairs 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

hou

-0.78

ahime

-0.76

 syndrome

-0.71

adian

-0.70

rigan

-0.68

ags

-0.67

ories

-0.67

anza

-0.65

erb

-0.64

ricane

-0.64

POSITIVE LOGITS

 notably

0.79

 namely

0.77

 preferably

0.76

 incidentally

0.72

 mathemat

0.69

 including

0.68

 evidenced

0.68

 comprising

0.67

including

0.67

 preferring

0.66

Activations Density 0.216%

instances of the word "both" in sentences comparing two entities or ideas

references to contrasting elements or pairs in various contexts

No Comments

No Known Activations