INDEX

Explanations

pronouns or nouns referring to people or entities

oai_token-act-pair · gpt-3.5-turbo

pronouns indicating agency and their associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

erno

-0.61

uesday

-0.58

requires

-0.54

ilings

-0.54

 complaining

-0.54

Sax

-0.53

raid

-0.53

 announcing

-0.53

LLOW

-0.50

arling

-0.50

POSITIVE LOGITS

to

1.04

 access

1.00

 unrestricted

0.98

 unlimited

0.97

 flexibility

0.95

 limitless

0.80

 freely

0.79

 freedom

0.78

to

0.77

 ample

0.73

Activations Density 0.160%

pronouns or nouns referring to people or entities

pronouns indicating agency and their associations

No Comments

No Known Activations