INDEX

Explanations

mentions of a specific term, possibly an abbreviation, that appears frequently in the text

oai_token-act-pair · gpt-3.5-turbo

terms and references related to the topic of "jobs" or "occupation."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Sakuya

-0.78

âĸ¬

-0.78

 Poles

-0.69

ART

-0.65

ãĥĥãĥī

-0.64

 Karin

-0.61

WAYS

-0.61

++++++++++++++++

-0.61

 breeze

-0.60

 Monarch

-0.60

POSITIVE LOGITS

essed

1.20

essions

1.08

poon

1.06

ession

1.06

idian

1.05

ols

1.05

ranch

1.04

anding

1.01

obs

1.00

ushi

0.99

Activations Density 0.007%

mentions of a specific term, possibly an abbreviation, that appears frequently in the text

terms and references related to the topic of "jobs" or "occupation."

No Comments

No Known Activations