INDEX

Explanations

phrases related to changes or regulations

oai_token-act-pair · gpt-3.5-turbo

forms of the verb "to be" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

çīĪ

-1.02

osate

-0.77

teness

-0.76

ALSE

-0.71

 Clarks

-0.64

 curiosity

-0.63

asio

-0.62

 pause

-0.62

 Nights

-0.62

 Nope

-0.62

POSITIVE LOGITS

 handled

1.36

 structured

1.20

 progressing

1.18

 shaping

1.18

 treated

1.17

 portrayed

1.17

 interpreted

1.13

 behaving

1.09

 impacting

1.08

 perceived

1.06

Activations Density 0.087%

phrases related to changes or regulations

forms of the verb "to be" in various contexts

No Comments

No Known Activations