INDEX

Explanations

repetitive instances of the word "same."

oai_token-act-pair · gpt-3.5-turbo

references to similarity or sameness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

*=-

-0.73

 Provided

-0.71

âĵĺ

-0.67

ohyd

-0.64

ases

-0.63

rend

-0.63

inders

-0.62

emi

-0.61

aire

-0.60

ç«

-0.60

POSITIVE LOGITS

 thing

0.98

 exact

0.97

 amount

0.91

 vein

0.90

 kind

0.80

 fate

0.73

 sorts

0.73

 kinds

0.73

ol

0.72

 timeframe

0.70

Activations Density 0.048%

repetitive instances of the word "same."

references to similarity or sameness

No Comments

No Known Activations