INDEX

Explanations

words related to partnerships or associations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "partner" 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

aston

-0.79

ux

-0.73

ibrary

-0.73

enery

-0.72

cott

-0.71

 oxide

-0.71

ãĥ©ãĥ³

-0.70

 Reincarn

-0.69

acco

-0.69

ihil

-0.67

POSITIVE LOGITS

 partner

1.01

 partners

0.99

hips

0.73

 Partner

0.73

 Stra

0.69

itute

0.65

ially

0.65

heses

0.63

atively

0.63

loo

0.63

Activations Density 0.022%

words related to partnerships or associations

instances of the word "partner" in various contexts

No Comments

No Known Activations