INDEX

Explanations

phrases related to continuation or expansion

oai_token-act-pair · gpt-3.5-turbo

phrases indicating continuity or ongoing processes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Poor

-0.58

 Drunk

-0.58

ixels

-0.58

uclear

-0.57

 forfeit

-0.55

 Saving

-0.55

 Oops

-0.55

icles

-0.54

 nick

-0.53

mint

-0.53

POSITIVE LOGITS

 throughout

1.21

 everywhere

1.10

 across

1.10

 extends

1.01

Across

0.97

 persists

0.92

 widest

0.90

 persisted

0.87

 Across

0.87

 persist

0.86

Activations Density 0.876%

phrases related to continuation or expansion

phrases indicating continuity or ongoing processes

No Comments

No Known Activations