INDEX

Explanations

phrases related to evaluating the quality or progress of a project or product

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate completion or assessment of products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

partisan

-0.77

 psychiatrists

-0.77

edia

-0.76

Democrats

-0.76

 Cosponsors

-0.75

 mayors

-0.72

govtrack

-0.70

illin

-0.69

Pew

-0.69

liberal

-0.68

POSITIVE LOGITS

 product

1.48

 project

1.32

 endeavor

1.12

 package

1.12

 products

1.08

 device

1.08

 operation

1.06

 item

1.05

 PRODUCT

1.04

 appliance

1.01

Activations Density 0.737%

phrases related to evaluating the quality or progress of a project or product

phrases that indicate completion or assessment of products

No Comments

No Known Activations