INDEX

Explanations

phrases related to support or endorsement

oai_token-act-pair · gpt-3.5-turbo

constructions involving the word "that."

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

 Doctrine

-0.69

EMBER

-0.67

LET

-0.63

Mech

-0.63

NES

-0.61

LY

-0.60

NAS

-0.58

ATH

-0.58

STE

-0.58

Brother

-0.58

POSITIVE LOGITS

 weren

1.10

 defy

1.06

 circulate

1.04

 aren

1.04

 arose

1.03

 comprise

1.03

 arise

1.03

 were

1.02

 resemble

1.00

 involve

1.00

Activations Density 0.205%

phrases related to support or endorsement

constructions involving the word "that."

No Comments

No Known Activations