INDEX

Explanations

phrases related to feedback or response to statements

oai_token-act-pair · gpt-3.5-turbo

expressions of appreciation and support for unity and collaboration

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

ãĥĺ

-0.81

 disappearance

-0.76

 ruining

-0.76

 revenge

-0.75

livion

-0.74

 thief

-0.71

 vanish

-0.71

digy

-0.71

 ruined

-0.70

die

-0.70

POSITIVE LOGITS

 bipartisan

1.29

 briefed

1.13

 constructive

1.13

 discussions

1.12

 consultations

1.12

 deliberations

1.11

 thoughtful

1.05

 consultation

1.03

 deliber

1.00

 counsel

0.99

Activations Density 0.789%

phrases related to feedback or response to statements

expressions of appreciation and support for unity and collaboration

No Comments

No Known Activations