INDEX

Explanations

information related to event details and locations

oai_token-act-pair · gpt-3.5-turbo

geographical references and physical locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 extraord

-0.62

 genius

-0.52

 ACPI

-0.48

 Junk

-0.48

 bastard

-0.48

 Muse

-0.47

 nutshell

-0.46

 alot

-0.46

 idiot

-0.45

 REALLY

-0.45

POSITIVE LOGITS

.''.

0.65

.</

0.63

engers

0.62

ipment

0.61

advertising

0.60

.).

0.59

imester

0.57

luster

0.55

lees

0.54

.<

0.54

Activations Density 1.618%

information related to event details and locations

geographical references and physical locations

No Comments

No Known Activations