INDEX

Explanations

words related to experience or expertise

oai_token-act-pair · gpt-3.5-turbo

references to experiences or events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

enegger

-0.72

 Crom

-0.71

 Hook

-0.65

 Freud

-0.63

 Carnival

-0.62

GROUND

-0.61

 sinking

-0.61

cock

-0.60

 Cock

-0.60

pul

-0.60

POSITIVE LOGITS

orters

1.44

orter

1.43

ropri

1.38

ository

1.25

onents

1.21

anse

1.20

iring

1.17

uls

1.15

ulsion

1.12

atri

1.11

Activations Density 0.011%

words related to experience or expertise

references to experiences or events

No Comments

No Known Activations