INDEX

Explanations

imperative verb phrases related to requests or demands

oai_token-act-pair · gpt-3.5-turbo

calls to action or requests for government or organizational intervention

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

Kop

-0.66

traumatic

-0.66

furt

-0.63

Flo

-0.63

ãĤ¼

-0.62

Got

-0.60

 Malk

-0.59

radio

-0.58

Talking

-0.57

 adolesc

-0.57

POSITIVE LOGITS

 reconsider

1.30

 investigate

1.14

 clarify

1.10

 intervene

1.07

 disclose

1.05

 revise

1.05

 undertake

1.04

 appoint

1.02

 abolish

0.97

 abandon

0.97

Activations Density 0.182%

imperative verb phrases related to requests or demands

calls to action or requests for government or organizational intervention

No Comments

No Known Activations