INDEX

Explanations

phrases related to risks, hazards, and potential harm

oai_token-act-pair · gpt-3.5-turbo

terms related to health risks and safety concerns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

swick

-0.76

Blocks

-0.71

lio

-0.68

vez

-0.67

ggles

-0.65

gdala

-0.63

atters

-0.62

vil

-0.62

ership

-0.62

FTWARE

-0.62

POSITIVE LOGITS

 incurred

1.20

 arising

1.15

 associated

1.12

 consequences

1.08

 attributable

1.06

 inherent

1.04

 outweigh

1.03

 outwe

1.00

 resulting

0.99

 stemming

0.98

Activations Density 0.271%

phrases related to risks, hazards, and potential harm

terms related to health risks and safety concerns

No Comments

No Known Activations