INDEX

Explanations

information or facts presented in a list format

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "are" 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 @ 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

culosis

-0.76

amphetamine

-0.72

iosity

-0.72

odder

-0.70

iture

-0.68

sed

-0.65

hate

-0.64

etheless

-0.62

aired

-0.62

akery

-0.61

POSITIVE LOGITS

 screenshots

0.87

 examples

0.83

 excerpts

0.76

 links

0.75

 snapshots

0.72

 excerpt

0.72

 quotes

0.70

 tentative

0.69

 hoping

0.68

 highlights

0.67

Activations Density 0.018%

information or facts presented in a list format

the repeated use of the word "are" in various contexts

No Comments

No Known Activations