INDEX

Explanations

phrases related to legal or ethical issues

oai_token-act-pair · gpt-3.5-turbo

references to consent and legal rights

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 tremend

-1.01

 millenn

-0.94

 princ

-0.89

©¶æ

-0.87

 exting

-0.85

oun

-0.79

 nomine

-0.78

 skelet

-0.78

 occas

-0.77

 tiss

-0.77

POSITIVE LOGITS

.(

0.97

.:

0.97

.–

0.97

.''.

0.88

.$

0.86

.--

0.85

.-

0.84

 attRot

0.84

.—

0.80

Activations Density 0.069%

phrases related to legal or ethical issues

references to consent and legal rights

No Comments

No Known Activations