INDEX

Explanations

mentions of specific locations or settings

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the" 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 @ 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

itiz

-0.70

emate

-0.66

ulence

-0.66

pointers

-0.64

witch

-0.63

anism

-0.63

antes

-0.62

pers

-0.60

ional

-0.60

irds

-0.60

POSITIVE LOGITS

 meantime

1.45

 midst

1.24

 aftermath

1.16

 absence

1.06

 guise

1.04

 simplest

1.04

 context

1.02

 same

0.97

 ensuing

0.95

 case

0.95

Activations Density 0.148%

mentions of specific locations or settings

occurrences of the word "the" in various contexts

No Comments

No Known Activations