INDEX

Explanations

the concept of justification or validation

oai_token-act-pair · gpt-3.5-turbo

terms related to validation and justification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

BOOK

-0.71

words

-0.65

 reperto

-0.65

 Advertisement

-0.64

master

-0.64

 versa

-0.63

 sandwiches

-0.63

duino

-0.61

 eater

-0.60

 cooker

-0.59

POSITIVE LOGITS

ication

2.07

icated

1.96

icating

1.84

icate

1.75

ications

1.66

icator

1.60

icates

1.59

ictive

1.54

icative

1.46

icators

1.46

Activations Density 0.055%

the concept of justification or validation

terms related to validation and justification

No Comments

No Known Activations