INDEX

Explanations

phrases related to permissions and legality

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate consent and coercion 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

elight

-0.80

onents

-0.72

rients

-0.70

 Components

-0.70

 Roller

-0.67

phis

-0.65

TPPStreamerBot

-0.64

imilation

-0.64

 Integ

-0.64

 Analy

-0.63

POSITIVE LOGITS

 circumstances

1.21

 compulsion

1.13

 whim

1.12

 necessity

1.07

 circumstance

1.06

 permission

1.05

chance

1.04

 pretext

1.04

 provocation

1.03

 mistaken

1.01

Activations Density 0.391%

phrases related to permissions and legality

phrases that indicate consent and coercion in various contexts

No Comments

No Known Activations