INDEX

Explanations

phrases indicating contrast or comparison

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the degree of significance or quantity

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

IFrame

Link

Negative Logits

ĪĴ

-1.02

İĭ

-0.94

etts

-0.80

cot

-0.72

çļ

-0.71

zanne

-0.70

ģĸ

-0.69

ĺħ

-0.67

bro

-0.67

gary

-0.66

POSITIVE LOGITS

 anymore

0.87

nor

0.77

 necessarily

0.68

 resembles

0.64

 ideologically

0.63

NESS

0.63

rance

0.62

thing

0.61

entity

0.61

 except

0.61

Activations Density 0.021%

phrases indicating contrast or comparison

phrases emphasizing the degree of significance or quantity

No Known Activations