INDEX

Explanations

strong emotions or opinions expressed in text

oai_token-act-pair · gpt-3.5-turbo

negative actions or statements related to inability or failure

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

Balance

-0.75

 recip

-0.68

Tokens

-0.67

ueless

-0.67

each

-0.66

Higher

-0.66

Compared

-0.65

balance

-0.64

Someone

-0.64

SpaceEngineers

-0.64

POSITIVE LOGITS

ashtra

0.73

 meanwhile

0.69

notations

0.68

 Bris

0.65

 Slate

0.64

Zub

0.63

 Tsarnaev

0.62

 Phant

0.62

 Eliot

0.61

Sut

0.59

Activations Density 0.547%

strong emotions or opinions expressed in text

negative actions or statements related to inability or failure

No Comments

No Known Activations