INDEX

Explanations

words related to news alerts and special reports

oai_token-act-pair · gpt-3.5-turbo

alerts and notifications related to news events

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

 monop

-0.70

 coerc

-0.64

 bene

-0.61

ivas

-0.60

theless

-0.57

itar

-0.56

 scapego

-0.55

 grate

-0.54

Sas

-0.54

 Sloan

-0.54

POSITIVE LOGITS

legram

0.67

ricanes

0.65

email

0.63

weather

0.63

enos

0.62

 subscribing

0.59

readable

0.59

 à¤

0.59

rill

0.58

urations

0.58

Activations Density 0.018%

words related to news alerts and special reports

alerts and notifications related to news events

No Comments

No Known Activations