INDEX

Explanations

terms related to policy, regulation, and oversight in various contexts

oai_token-act-pair · gpt-3.5-turbo

keywords related to regulatory frameworks and governance

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Jr

-0.62

arnaev

-0.62

 Klux

-0.62

 Sour

-0.60

undreds

-0.59

 Slim

-0.59

anan

-0.58

ovember

-0.57

erald

-0.57

itialized

-0.57

POSITIVE LOGITS

etc

0.78

worthiness

0.76

Frames

0.66

'."

0.65

.''.

0.65

 accordingly

0.65

flows

0.64

 outcomes

0.64

]).

0.64

 behaviours

0.64

Activations Density 0.770%

terms related to policy, regulation, and oversight in various contexts

keywords related to regulatory frameworks and governance

No Comments

No Known Activations