INDEX

Explanations

specific mentions of the letter "A" followed by a high activation value

oai_token-act-pair · gpt-3.5-turbo

occurrences of the character "A" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 appointments

-0.68

 outlets

-0.66

oids

-0.66

 stripes

-0.65

 engagements

-0.64

 offenses

-0.63

 assemblies

-0.61

 interests

-0.60

 incomes

-0.60

 electrodes

-0.60

POSITIVE LOGITS

chieve

1.33

ircraft

1.30

UTH

1.27

erial

1.25

uckland

1.23

ctors

1.22

gency

1.21

ctions

1.15

pex

1.10

ffect

1.09

Activations Density 0.108%

specific mentions of the letter "A" followed by a high activation value

occurrences of the character "A" in various contexts

No Comments

No Known Activations