INDEX

Explanations

entities or concepts with the power or authority to do something

oai_token-act-pair · gpt-3.5-turbo

phrases related to power and authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

CTV

-0.82

quickShipAvailable

-0.79

ãĤ¼

-0.72

ELD

-0.71

existent

-0.71

éļ

-0.68

CI

-0.67

equ

-0.66

ENTION

-0.66

Cas

-0.66

POSITIVE LOGITS

 negotiate

1.07

 nominate

1.05

 declare

0.97

 determine

0.96

 revoke

0.93

 impose

0.93

 create

0.93

 make

0.92

 accelerate

0.92

 withstand

0.91

Activations Density 0.126%

entities or concepts with the power or authority to do something

phrases related to power and authority

No Comments

No Known Activations