INDEX

Explanations

references to different types of vehicles or technologies

oai_token-act-pair · gpt-3.5-turbo

names or titles that signify rank or classification 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

risk

-0.68

Nap

-0.66

KEY

-0.66

pak

-0.64

pu

-0.63

kil

-0.62

political

-0.61

emet

-0.60

ONEY

-0.60

eas

-0.59

POSITIVE LOGITS

llor

0.84

tenance

0.84

ertodd

0.83

terday

0.79

ODUCT

0.79

ificate

0.78

osterone

0.74

riors

0.72

ocobo

0.72

quished

0.71

Activations Density 0.248%

references to different types of vehicles or technologies

names or titles that signify rank or classification in various contexts

No Comments

No Known Activations