INDEX

Explanations

words related to making adjustments or variations

oai_token-act-pair · gpt-3.5-turbo

terms related to making modifications or changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

gom

-0.78

NetMessage

-0.77

utra

-0.75

chu

-0.72

ijk

-0.70

irez

-0.70

ī

-0.68

ciating

-0.67

intel

-0.67

cade

-0.67

POSITIVE LOGITS

 accordingly

1.02

 adjustments

0.92

 adjusts

0.87

 downwards

0.87

ments

0.85

 adjusting

0.84

 adjustment

0.83

 downward

0.80

 adjust

0.80

 adjusted

0.78

Activations Density 0.037%

words related to making adjustments or variations

terms related to making modifications or changes

No Comments

No Known Activations