INDEX

Explanations

occurrences of numbers or numerical sequences

oai_token-act-pair · gpt-3.5-turbo

connections to significant historical events or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ļéĨĴ

-0.76

 versa

-0.68

ogether

-0.68

_.

-0.67

nown

-0.66

xxxx

-0.65

 challeng

-0.64

qus

-0.63

akespe

-0.63

jri

-0.63

POSITIVE LOGITS

 Belfast

0.87

 Hillary

0.73

 Donald

0.72

NRL

0.70

 Xperia

0.69

 Transgender

0.68

 âĢº

0.67

 Fukushima

0.66

Â¶

0.66

UFC

0.65

Activations Density 1.168%

occurrences of numbers or numerical sequences

connections to significant historical events or statistics

No Comments

No Known Activations