INDEX

Explanations

words related to transportation stops, such as train stops, bus stops, or airplane stops

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "stop" and its 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ighth

-0.78

yss

-0.74

 abund

-0.72

rity

-0.70

 suscept

-0.70

aths

-0.67

xual

-0.65

 reconc

-0.64

 enthusi

-0.63

ophon

-0.62

POSITIVE LOGITS

watch

1.03

gap

0.98

oppers

0.87

lights

0.79

opping

0.73

ions

0.73

watching

0.70

down

0.69

fires

0.69

kick

0.69

Activations Density 0.028%

words related to transportation stops, such as train stops, bus stops, or airplane stops

occurrences of the word "stop" and its variations

No Comments

No Known Activations