INDEX

Explanations

instances in the text where a statement or opinion is being shared or indicated by the presence of sentence-ending punctuation

oai_token-act-pair · gpt-3.5-turbo

statements related to opinions or commentary within a dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

¥µ

-0.72

aten

-0.67

 downright

-0.66

 ingest

-0.66

 proverbial

-0.65

 horrend

-0.64

 indoctr

-0.64

zona

-0.62

 eleph

-0.62

 everyday

-0.62

POSITIVE LOGITS

However

1.14

Asked

1.12

Labour

1.09

Officials

1.07

Meanwhile

1.06

Earlier

1.04

Speaking

1.02

CVE

1.01

Refer

1.00

Â©

0.98

Activations Density 0.563%

instances in the text where a statement or opinion is being shared or indicated by the presence of sentence-ending punctuation

statements related to opinions or commentary within a dialogue

No Comments

No Known Activations