INDEX

Explanations

words related to announcements and verbal declarations

oai_token-act-pair · gpt-3.5-turbo

references to measurement units, particularly those related to fluid ounces

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

acea

-1.00

otherapy

-0.87

itaire

-0.83

Downloadha

-0.80

gew

-0.75

ocr

-0.72

icum

-0.71

iciency

-0.70

omon

-0.70

ocide

-0.69

POSITIVE LOGITS

ment

1.02

ments

0.98

theless

0.79

sburg

0.79

rers

0.78

prise

0.78

MENTS

0.74

ounce

0.72

prises

0.71

mare

0.71

Activations Density 0.049%

words related to announcements and verbal declarations

references to measurement units, particularly those related to fluid ounces

No Comments

No Known Activations