INDEX

Explanations

words related to ingestion or consumption, especially of a significant or engulfing nature

oai_token-act-pair · gpt-3.5-turbo

terms related to consuming or ingesting

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

senal

-0.71

 psychiat

-0.70

romy

-0.69

 Degree

-0.67

 diligence

-0.66

actionDate

-0.64

CTV

-0.64

iances

-0.63

Weather

-0.63

Tech

-0.62

POSITIVE LOGITS

ipes

0.92

meat

0.89

ritten

0.86

 chunks

0.83

gum

0.83

 swallow

0.81

 pork

0.81

 vines

0.81

 flakes

0.80

tails

0.79

Activations Density 0.083%

words related to ingestion or consumption, especially of a significant or engulfing nature

terms related to consuming or ingesting

No Comments

No Known Activations