INDEX

Explanations

mentions of legal or political terms

oai_token-act-pair · gpt-3.5-turbo

definitive statements and claims

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

usercontent

-0.80

dule

-0.79

MpServer

-0.74

fecture

-0.72

quished

-0.72

ogether

-0.71

 Skydragon

-0.71

rollers

-0.71

affle

-0.71

ickets

-0.70

POSITIVE LOGITS

 assertion

1.51

 sentiment

1.21

 statement

1.17

 implication

1.16

 phrase

1.16

 affirmation

1.13

 premise

1.13

 argument

1.12

 proposition

1.11

 mantra

1.10

Activations Density 0.407%

mentions of legal or political terms

definitive statements and claims

No Comments

No Known Activations