INDEX

Explanations

phrases related to having no hesitation to perform an action

oai_token-act-pair · gpt-3.5-turbo

phrases indicating certainty or a lack of hesitation

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

arov

-0.67

EStream

-0.61

Downloadha

-0.58

obal

-0.58

glomer

-0.57

ossible

-0.57

ode

-0.56

 teasp

-0.56

Nev

-0.55

Network

-0.54

POSITIVE LOGITS

mberg

0.81

-->

0.75

kers

0.71

 tragedies

0.68

iery

0.68

steen

0.65

 Stras

0.65

lein

0.63

ingen

0.62

amaz

0.61

Activations Density 0.223%

phrases related to having no hesitation to perform an action

phrases indicating certainty or a lack of hesitation

No Comments

No Known Activations