INDEX

Explanations

words related to policies, legislation, and governmental programs

oai_token-act-pair · gpt-3.5-turbo

terms related to healthcare plans and enrollment metrics

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

 microscope

-0.65

 Bane

-0.65

 blasphemy

-0.64

THING

-0.61

 Potion

-0.61

 Canaver

-0.61

 dossier

-0.61

 defamation

-0.61

 Assass

-0.60

 sorcery

-0.60

POSITIVE LOGITS

goers

1.35

 residents

1.34

arers

1.30

 users

1.28

 participants

1.20

 subscribers

1.18

users

1.16

 customers

1.16

 recipients

1.16

 learners

1.15

Activations Density 0.839%

words related to policies, legislation, and governmental programs

terms related to healthcare plans and enrollment metrics

No Comments

No Known Activations