INDEX

Explanations

phrases asking or referring to the type or category of something

oai_token-act-pair · gpt-3.5-turbo

inquiries about types or categories of things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

chy

-0.74

obyl

-0.73

VEL

-0.71

MY

-0.67

Knight

-0.66

heid

-0.66

ederation

-0.66

 Byrne

-0.63

enez

-0.62

anyon

-0.62

POSITIVE LOGITS

etting

0.78

liest

0.72

faces

0.65

isodes

0.64

soever

0.63

rous

0.62

hearted

0.62

?]

0.62

 happ

0.62

 ---------

0.62

Activations Density 0.012%

phrases asking or referring to the type or category of something

inquiries about types or categories of things

No Comments

No Known Activations