INDEX

Explanations

phrases related to assumptions

oai_token-act-pair · gpt-3.5-turbo

references to societal or cultural assumptions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Interstitial

-0.99

sung

-0.88

thumbnails

-0.80

CLASSIFIED

-0.77

waters

-0.77

ansk

-0.74

oho

-0.73

dos

-0.71

ateurs

-0.70

HCR

-0.70

POSITIVE LOGITS

 assumptions

1.07

 assumption

1.00

 premise

0.86

 underpin

0.85

 biases

0.81

 presupp

0.78

 disclaimer

0.74

 assumes

0.71

 underlying

0.69

lessly

0.68

Activations Density 0.025%

phrases related to assumptions

references to societal or cultural assumptions

No Comments

No Known Activations