INDEX

Explanations

the specific phrase or phrases mentioned in the activation

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of phrases and their variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ÄŁ

-0.81

DERR

-0.77

 Emirates

-0.72

llah

-0.70

 Thro

-0.69

 hemor

-0.68

fman

-0.67

Fal

-0.66

 Indies

-0.65

 Brotherhood

-0.62

POSITIVE LOGITS

phrase

1.06

ology

1.03

 phrases

1.01

 phrase

0.91

witz

0.89

terday

0.84

stress

0.82

mith

0.81

atre

0.78

 uttered

0.78

Activations Density 0.021%

the specific phrase or phrases mentioned in the activation

repeated mentions of phrases and their variations

No Comments

No Known Activations