INDEX

Explanations

terms related to continuity

oai_token-act-pair · gpt-3.5-turbo

the word "continue" and its variations, indicating ongoing actions or states

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

Reviewer

-0.87

*/(

-0.77

eah

-0.69

ouls

-0.68

inj

-0.65

IDS

-0.64

sters

-0.63

 puppies

-0.62

 forfeit

-0.61

 doct

-0.61

POSITIVE LOGITS

uously

1.21

uous

1.19

uity

1.16

uum

1.13

uation

1.12

uing

1.09

ued

1.03

ually

1.03

ual

1.01

uations

0.97

Activations Density 0.035%

terms related to continuity

the word "continue" and its variations, indicating ongoing actions or states

No Comments

No Known Activations