INDEX

Explanations

mentions or descriptions of individuals labeled as "seasoned" or experienced in a particular field

oai_token-act-pair · gpt-3.5-turbo

words associated with experience and expertise

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

ples

-0.80

rador

-0.80

arters

-0.78

ble

-0.77

pps

-0.75

arations

-0.75

pler

-0.73

redit

-0.73

lde

-0.73

orer

-0.73

POSITIVE LOGITS

à©

0.81

senal

0.78

 à¨

0.75

à¨

0.73

ãĤ¤ãĥĪ

0.72

Â¯Â¯Â¯Â¯

0.70

APH

0.70

 weary

0.70

0.69

 inacc

0.69

Activations Density 0.023%

mentions or descriptions of individuals labeled as "seasoned" or experienced in a particular field

words associated with experience and expertise

No Comments

No Known Activations