INDEX

Explanations

phrases describing the act of publicly criticizing or condemning someone or something

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "call out."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

olars

-0.75

 gamble

-0.72

antry

-0.68

 princip

-0.65

 fall

-0.63

anos

-0.63

 mint

-0.60

agan

-0.59

 sleeve

-0.59

fing

-0.59

POSITIVE LOGITS

stretched

1.06

 loud

0.92

posts

0.74

worn

0.71

fitted

0.71

 loudly

0.68

unci

0.68

STDOUT

0.67

wards

0.67

lier

0.67

Activations Density 0.017%

phrases describing the act of publicly criticizing or condemning someone or something

instances of the phrase "call out."

No Comments

No Known Activations