INDEX

Explanations

references to things or people known for specific characteristics or actions

oai_token-act-pair · gpt-3.5-turbo

phrases or terms that indicate reputation or recognition for various entities or individuals

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

brainer

-0.67

requisites

-0.64

needed

-0.64

 PLEASE

-0.63

adjust

-0.60

CNN

-0.60

req

-0.60

MRI

-0.60

 suppose

-0.59

 UPDATE

-0.59

POSITIVE LOGITS

negie

0.79

 unorthodox

0.73

 impecc

0.72

 outspoken

0.69

 nickname

0.69

 excellence

0.66

 colorful

0.65

 colourful

0.65

 underdog

0.64

 eccentric

0.64

Activations Density 0.459%

references to things or people known for specific characteristics or actions

phrases or terms that indicate reputation or recognition for various entities or individuals

No Comments

No Known Activations