INDEX

Explanations

words related to testing or experimentation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "test" and its variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

taboola

-0.74

lance

-0.67

justice

-0.62

wikipedia

-0.61

joining

-0.60

lihood

-0.60

theless

-0.60

 acknow

-0.59

 Mysteries

-0.59

brance

-0.58

POSITIVE LOGITS

osterone

1.20

imony

0.97

imon

0.90

ifies

0.84

orously

0.80

icle

0.77

rador

0.76

udo

0.76

icles

0.75

 hypotheses

0.74

Activations Density 0.038%

words related to testing or experimentation

instances of the word "test" and its variants

No Comments

No Known Activations