INDEX

Explanations

phrases indicating lack of association or correlation

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a lack of relevance or connection to a particular topic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ahime

-0.63

members

-0.61

////////////////////////////////

-0.59

riger

-0.59

aii

-0.59

 crafted

-0.57

 toget

-0.56

aniel

-0.56

updated

-0.56

ement

-0.55

POSITIVE LOGITS

 differentiate

0.82

 distract

0.81

 worry

0.78

 celebrate

0.77

 complain

0.76

 conserve

0.75

 hide

0.75

 hinder

0.74

 envy

0.73

 interfere

0.73

Activations Density 0.060%

phrases indicating lack of association or correlation

phrases that indicate a lack of relevance or connection to a particular topic

No Comments

No Known Activations