INDEX

Explanations

phrases related to collective or shared concepts

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "common."

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

agate

-0.85

asus

-0.82

enda

-0.81

gur

-0.78

hyde

-0.76

otos

-0.74

resy

-0.74

endas

-0.73

ocalypse

-0.72

cember

-0.72

POSITIVE LOGITS

wealth

1.46

alities

1.10

 denomin

1.04

 ancestor

1.01

ensical

1.00

places

0.97

ality

0.97

 decency

0.87

place

0.86

 occurrence

0.80

Activations Density 0.019%

phrases related to collective or shared concepts

the repeated use of the word "common."

No Comments

No Known Activations