INDEX

Explanations

moments or instances within a text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "moments" in various contexts

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

raid

-0.83

ledge

-0.76

backer

-0.73

achev

-0.71

toe

-0.71

yright

-0.71

tymology

-0.70

ksh

-0.70

handle

-0.70

ply

-0.69

POSITIVE LOGITS

 moments

1.16

 Moments

0.91

hift

0.90

 bouts

0.88

 glimps

0.84

 Minutes

0.83

 milestones

0.82

 reminders

0.82

 involving

0.81

 Scenes

0.80

Activations Density 0.057%

moments or instances within a text

instances of the word "moments" in various contexts

No Comments

No Known Activations