INDEX

Explanations

informational statements that begin with the word "Every"

oai_token-act-pair · gpt-3.5-turbo

the word "Every" in varied contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

olas

-0.70

 Metatron

-0.66

ket

-0.66

mit

-0.61

que

-0.59

 Roberts

-0.59

tein

-0.58

 à¤

-0.58

Viz

-0.58

aic

-0.57

POSITIVE LOGITS

THING

1.36

where

1.07

ursday

0.98

WHERE

0.93

body

0.90

ĪĴ

0.90

ĸļ

0.86

 conceivable

0.85

etheless

0.84

eatures

0.81

Activations Density 0.021%

informational statements that begin with the word "Every"

the word "Every" in varied contexts

No Comments

No Known Activations