INDEX

Explanations

expressions related to exaggeration or intensity

oai_token-act-pair · gpt-3.5-turbo

intensifiers that convey extreme qualities or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ividual

-0.75

tein

-0.73

itu

-0.68

tan

-0.67

hammad

-0.66

OTOS

-0.66

sein

-0.66

 Annotations

-0.65

Semitism

-0.65

olan

-0.65

POSITIVE LOGITS

efully

0.81

 wildly

0.78

 inaccurate

0.76

ishly

0.71

uously

0.69

 combust

0.68

 impractical

0.67

assi

0.67

 exagger

0.65

 inco

0.64

Activations Density 0.008%

expressions related to exaggeration or intensity

intensifiers that convey extreme qualities or states

No Comments

No Known Activations