INDEX

Explanations

names and titles of significant individuals in various contexts

oai_token-act-pair · gpt-3.5-turbo

proper names and significant titles in the text

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

anwhile

-0.70

ģĸ

-0.68

etheless

-0.64

ĸļ

-0.62

iculty

-0.61

mble

-0.58

 guid

-0.57

Ħ¢

-0.56

£ı

-0.55

*.

-0.55

POSITIVE LOGITS

ona

0.70

 Street

0.69

Fest

0.65

ont

0.63

Fit

0.63

cup

0.63

Star

0.62

Wiki

0.61

Ps

0.60

Coin

0.60

Activations Density 0.558%

names and titles of significant individuals in various contexts

proper names and significant titles in the text

No Comments

No Known Activations