INDEX

Explanations

phrases indicating the exclusion or negation of something

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate the act of not excluding possibilities

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

awar

-0.81

cue

-0.79

ombat

-0.78

artist

-0.75

eatured

-0.72

eworld

-0.71

omsky

-0.70

Eye

-0.70

oppy

-0.70

MAS

-0.69

POSITIVE LOGITS

 anything

0.78

posts

0.74

 outright

0.70

enance

0.69

EVs

0.69

 smoking

0.68

 foul

0.67

any

0.66

 extradition

0.66

 hypot

0.66

Activations Density 0.027%

phrases indicating the exclusion or negation of something

phrases that indicate the act of not excluding possibilities

No Comments

No Known Activations