INDEX

Explanations

phrases or entities containing a hyphen followed by a numerical value indicative of ranking or grouping

oai_token-act-pair · gpt-3.5-turbo

negative or derogatory terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 ballpark

-0.77

 caution

-0.75

 expend

-0.70

 divest

-0.69

 operating

-0.68

 share

-0.68

 debit

-0.67

 supper

-0.67

 drink

-0.66

 breakfast

-0.66

POSITIVE LOGITS

sama

1.45

san

1.31

kun

1.25

chan

1.21

based

1.14

shaped

1.13

Lago

1.10

derived

1.07

style

1.06

vous

1.05

Activations Density 0.097%

phrases or entities containing a hyphen followed by a numerical value indicative of ranking or grouping

negative or derogatory terms

No Comments

No Known Activations