INDEX

Explanations

the word "random"

oai_token-act-pair · gpt-3.5-turbo

concepts related to randomness

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

ossier

-0.80

PRO

-0.77

SHARE

-0.75

raints

-0.73

rex

-0.73

IDS

-0.71

yer

-0.71

ept

-0.71

hid

-0.70

ippi

-0.70

POSITIVE LOGITS

istically

1.05

 assortment

0.96

aneously

0.96

 randomly

0.94

 random

0.90

ised

0.87

isable

0.83

izable

0.83

aneous

0.74

 strangers

0.73

Activations Density 0.015%

the word "random"

concepts related to randomness

No Comments

No Known Activations