INDEX

Explanations

words related to distribution or dispersal

oai_token-act-pair · gpt-3.5-turbo

variations of the word "dispense."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Reviewer

-0.86

rium

-0.78

lihood

-0.75

sen

-0.74

66666666

-0.73

HCR

-0.72

FORE

-0.71

geist

-0.71

Downloadha

-0.69

tle

-0.69

POSITIVE LOGITS

ersion

1.01

 disp

1.00

ensed

0.94

ossession

0.85

atches

0.82

assion

0.81

atching

0.81

orter

0.81

abled

0.80

ennes

0.78

Activations Density 0.008%

words related to distribution or dispersal

variations of the word "dispense."

No Comments

No Known Activations