INDEX

Explanations

pieces of text related to ratings or feedback

oai_token-act-pair · gpt-3.5-turbo

numeric values and ratings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 eleph

-0.71

 dotted

-0.62

oun

-0.58

 weld

-0.54

etheless

-0.54

ò

-0.53

 occas

-0.53

 secretaries

-0.53

.""

-0.52

 Â®

-0.51

POSITIVE LOGITS

Invalid

0.72

prem

0.69

dayName

0.69

PROV

0.68

Prev

0.67

thinkable

0.67

pmwiki

0.66

Posted

0.65

Rating

0.64

roo

0.64

Activations Density 0.367%

pieces of text related to ratings or feedback

numeric values and ratings

No Comments

No Known Activations