INDEX

Explanations

adjectives describing opinions or evaluations of experience

oai_token-act-pair · gpt-3.5-turbo

adjectives and adverbs that convey positive and negative evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ãĥĺãĥ©

-0.71

asio

-0.66

adj

-0.66

 Abstract

-0.66

uce

-0.60

Domain

-0.60

ãĥ¯ãĥ³

-0.59

bert

-0.59

uction

-0.59

################################

-0.58

POSITIVE LOGITS

 lately

1.18

 fruitful

0.99

 since

0.99

 unsuccessful

0.88

 successful

0.82

 steady

0.81

 dogged

0.77

 steadily

0.76

 consistent

0.74

 productive

0.72

Activations Density 0.268%

adjectives describing opinions or evaluations of experience

adjectives and adverbs that convey positive and negative evaluations

No Comments

No Known Activations