INDEX

Explanations

mentions of specific names and locations

oai_token-act-pair · gpt-3.5-turbo

locations and geographical references

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

hower

-0.69

ĸļ

-0.64

©¶æ

-0.63

usercontent

-0.60

ensional

-0.57

 thirds

-0.57

sheets

-0.56

 Creed

-0.55

 behold

-0.54

sheet

-0.54

POSITIVE LOGITS

arios

0.86

illas

0.80

lia

0.79

ela

0.78

chio

0.76

aukee

0.74

essim

0.74

achu

0.71

ongyang

0.71

udo

0.70

Activations Density 0.184%

mentions of specific names and locations

locations and geographical references

No Comments

No Known Activations