INDEX

Explanations

phrases related to safety measures or methods

oai_token-act-pair · gpt-3.5-turbo

phrases indicating methods, precautions, or ways of achieving something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

abases

-0.89

xus

-0.88

liam

-0.75

itars

-0.75

olas

-0.75

nces

-0.72

istries

-0.71

doms

-0.71

tails

-0.70

otin

-0.70

POSITIVE LOGITS

 progresses

0.89

 reminder

0.87

 opener

0.77

 multiplier

0.73

 indicator

0.72

 conduit

0.72

 starter

0.72

 distingu

0.71

 distraction

0.69

 identifier

0.69

Activations Density 0.195%

phrases related to safety measures or methods

phrases indicating methods, precautions, or ways of achieving something

No Comments

No Known Activations