INDEX

Explanations

statements or descriptions using the word "a" or "an" followed by a noun

oai_token-act-pair · gpt-3.5-turbo

the letter 'a'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Allied

-0.71

 Atkins

-0.70

EVs

-0.69

 Abbey

-0.62

reports

-0.61

 advis

-0.60

 Abortion

-0.60

 Everton

-0.60

 Oscar

-0.59

 infield

-0.59

POSITIVE LOGITS

usterity

1.13

uras

1.10

vertisement

1.10

merce

1.08

ria

1.06

rouse

1.03

ird

0.95

hem

0.94

unts

0.93

ctors

0.90

Activations Density 0.149%

statements or descriptions using the word "a" or "an" followed by a noun

the letter 'a'

No Comments

No Known Activations