INDEX

Explanations

words or abbreviations related to legislative or organizational matters

oai_token-act-pair · gpt-3.5-turbo

occurrences of the acronym "AB" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 explan

-0.73

ician

-0.70

ancial

-0.68

arium

-0.65

omore

-0.64

ciating

-0.64

perse

-0.64

 Gors

-0.63

icians

-0.61

andum

-0.60

POSITIVE LOGITS

RIC

1.13

yrinth

1.06

stract

1.05

STR

1.03

uilt

1.00

RAM

1.00

ORN

0.93

LES

0.90

UL

0.89

OUT

0.89

Activations Density 0.014%

words or abbreviations related to legislative or organizational matters

occurrences of the acronym "AB" in various contexts

No Comments

No Known Activations