INDEX

Explanations

phrases related to problems, controversy, turmoil, and negative situations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating ongoing issues or controversies

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

Reviewer

-0.81

ivery

-0.67

LY

-0.66

Desk

-0.64

done

-0.64

 usable

-0.64

lex

-0.64

OTAL

-0.61

atform

-0.60

ovo

-0.60

POSITIVE LOGITS

 plague

1.21

 ensued

1.20

 engulf

1.19

 plagued

1.17

 surrounds

1.16

 accompanies

1.12

 engulfed

1.08

 perv

1.07

 arose

1.07

 preceded

1.04

Activations Density 0.198%

phrases related to problems, controversy, turmoil, and negative situations

phrases indicating ongoing issues or controversies

No Comments

No Known Activations