INDEX

Explanations

adjectives to describe negative or controversial situations

oai_token-act-pair · gpt-3.5-turbo

negative descriptors and terms related to transparency and accountability

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

 Â«

-0.67

.).

-0.67

 ï¿½

-0.67

.):

-0.66

.),

-0.64

 ãĢĮ

-0.63

arnaev

-0.62

.)

-0.60

essage

-0.59

Phys

-0.58

POSITIVE LOGITS

2.24

"?

1.92

",

1.86

"!

1.81

"-

1.79

"...

1.76

"—

1.75

":

1.68

".

1.67

"âĢ¦

1.67

Activations Density 0.622%

adjectives to describe negative or controversial situations

negative descriptors and terms related to transparency and accountability

No Comments

No Known Activations