INDEX

Explanations

phrases related to specific names or terms

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

•EggList

No Comments

Negative Logits

 Jung

-0.79

GO

-0.78

 Maher

-0.76

Joh

-0.74

TIM

-0.72

ham

-0.72

HAL

-0.71

 Huang

-0.70

 JACK

-0.69

Jen

-0.69

POSITIVE LOGITS

ic

1.67

IC

1.33

ics

1.25

ici

1.18

icc

1.17

aic

1.16

icism

1.16

icity

1.15

ICS

1.11

inic

1.11

Activations Density 0.194%

phrases related to specific names or terms

proper nouns, particularly names and titles

No Comments

No Known Activations