INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

references to political figures and actions

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

\">

-0.83

Bang

-0.81

è¦ļéĨĴ

-0.78

ORPG

-0.75

maps

-0.73

forestation

-0.73

piracy

-0.73

ãĥ¥

-0.73

ãĤ¨ãĥ«

-0.72

ãĥĵ

-0.72

POSITIVE LOGITS

 disingen

1.21

 dishon

1.07

 perjury

1.05

 condesc

1.03

 dishonest

1.03

 rhetorical

1.02

 rebuke

1.02

 coward

1.02

 repud

1.01

 hypocrisy

1.00

Activations Density 0.955%

proper nouns or names

references to political figures and actions

No Comments

No Known Activations