INDEX

Explanations

anomalies or discrepancies within a text, as indicated by non-standard characters

oai_token-act-pair · gpt-3.5-turbo

instances of contextually significant quotes or statements about various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 commissions

-0.74

 cens

-0.71

 enlist

-0.70

 censored

-0.69

 honored

-0.69

 seams

-0.69

 joint

-0.68

 wound

-0.68

 discontinued

-0.67

 subsidized

-0.67

POSITIVE LOGITS

"[

1.45

"(

1.44

1.33

"'

1.28

Refer

1.24

READ

1.24

Read

1.23

Advertisement

1.23

Shape

1.21

Article

1.21

Activations Density 0.108%

anomalies or discrepancies within a text, as indicated by non-standard characters

instances of contextually significant quotes or statements about various topics

No Comments

No Known Activations