INDEX

Explanations

statements about confirming or denying specific conditions or actions

oai_token-act-pair · gpt-3.5-turbo

phrases questioning the validity or existence of something

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

ĸļ

-0.89

comings

-0.79

¸

-0.77

nikov

-0.74

 srfAttach

-0.71

äºĶ

-0.70

-0.69

undrum

-0.69

ãĤ¼ãĤ¦ãĤ¹

-0.66

SourceFile

-0.66

POSITIVE LOGITS

 they

0.87

 existed

0.77

 there

0.77

you

0.77

 qualifies

0.75

 technically

0.75

we

0.70

 swayed

0.70

 necessarily

0.68

 exists

0.67

Activations Density 0.025%

statements about confirming or denying specific conditions or actions

phrases questioning the validity or existence of something

No Comments

No Known Activations