INDEX

Explanations

verbs related to influencing or persuading others to take action

oai_token-act-pair · gpt-3.5-turbo

the word "to" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

quickShipAvailable

-0.81

soDeliveryDate

-0.80

SourceFile

-0.77

Cooldown

-0.74

TION

-0.69

croft

-0.64

 surges

-0.64

imental

-0.62

washer

-0.61

 beginnings

-0.61

POSITIVE LOGITS

 whom

1.12

 engage

1.04

 undertake

0.96

 defend

0.95

 emulate

0.93

iling

0.93

ggles

0.93

 identify

0.93

 pursue

0.92

 assist

0.92

Activations Density 0.252%

verbs related to influencing or persuading others to take action

the word "to" in various contexts

No Comments

No Known Activations