INDEX

Explanations

phrases related to comparing different entities or groups

oai_token-act-pair · gpt-3.5-turbo

the term "respective" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ertodd

-0.87

arer

-0.85

uve

-0.81

lam

-0.80

something

-0.75

avis

-0.75

ker

-0.75

fitting

-0.75

toc

-0.74

cher

-0.73

POSITIVE LOGITS

 strengths

1.02

 respective

1.01

 halves

0.94

 branches

0.92

 sides

0.90

 spheres

0.88

 administrations

0.87

 constituencies

0.86

 merits

0.86

 counterparts

0.85

Activations Density 0.029%

phrases related to comparing different entities or groups

the term "respective" in various contexts

No Comments

No Known Activations