INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

references to news agencies and photo credits

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

FML

-0.71

 Warcraft

-0.65

 Transformers

-0.64

 Haram

-0.63

pard

-0.60

keley

-0.59

lbs

-0.57

LSD

-0.55

addons

-0.54

 roses

-0.53

POSITIVE LOGITS

Rap

0.70

odox

0.70

senal

0.65

icio

0.64

Balt

0.64

ãĤ¯

0.62

onde

0.61

Í

0.61

imil

0.61

0.60

Activations Density 0.180%

proper nouns or names

references to news agencies and photo credits

No Comments

No Known Activations