INDEX

Explanations

words related to exclusion or being excluded

oai_token-act-pair · gpt-3.5-turbo

terms related to exclusion or being excluded

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

oÄŁ

-0.89

ingham

-0.74

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.73

nan

-0.73

 deed

-0.72

vous

-0.70

hran

-0.70

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.69

ebus

-0.68

Ì¶

-0.68

POSITIVE LOGITS

 exclude

0.99

 excludes

0.90

ively

0.85

 excluding

0.85

 excluded

0.83

 spoilers

0.83

 prejudice

0.79

 exclus

0.78

 minded

0.77

 hypoc

0.75

Activations Density 0.006%

words related to exclusion or being excluded

terms related to exclusion or being excluded

No Comments

No Known Activations