INDEX

Explanations

phrases related to seeking and delivering justice

oai_token-act-pair · gpt-3.5-turbo

phrases and terms related to justice and accountability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Supplement

-0.82

pse

-0.71

 Sturgeon

-0.70

acly

-0.69

alg

-0.65

imester

-0.61

NetMessage

-0.61

 Echoes

-0.61

 Digest

-0.60

 Flex

-0.60

POSITIVE LOGITS

 punished

1.49

 prosecuted

1.36

 accountable

1.29

 jailed

1.27

 apprehended

1.19

 indicted

1.16

 arrested

1.15

 justice

1.14

 imprisoned

1.13

 repent

1.12

Activations Density 0.334%

phrases related to seeking and delivering justice

phrases and terms related to justice and accountability

No Comments

No Known Activations