INDEX

Explanations

words related to characteristics or descriptions of things

oai_token-act-pair · gpt-3.5-turbo

concepts related to types and categories of experiences or phenomena

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

)</

-0.72

 Signs

-0.70

ummies

-0.65

oppers

-0.62

eatures

-0.62

%);

-0.62

SQ

-0.62

 Shed

-0.62

ovember

-0.61

ebus

-0.59

POSITIVE LOGITS

 imaginable

0.72

 shenan

0.70

 depending

0.67

 guiActiveUnfocused

0.67

Â·Â·

0.66

manship

0.65

yip

0.65

ivalry

0.62

IBLE

0.60

 arrangement

0.60

Activations Density 0.260%

words related to characteristics or descriptions of things

concepts related to types and categories of experiences or phenomena

No Comments

No Known Activations