INDEX

Explanations

accents or special characters

oai_token-act-pair · gpt-3.5-turbo

various symbols and special characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 poisoning

-0.74

 nursery

-0.73

 velvet

-0.71

 bonded

-0.71

 shroud

-0.70

wig

-0.69

 bitters

-0.65

 deed

-0.65

wagen

-0.64

 makeup

-0.64

POSITIVE LOGITS

£

1.16

¾

1.04

Ħ

1.03

Ķ

0.98

ł

0.98

¼

0.94

Ĥ

0.94

¸

0.94

Ģ

0.93

ĺ

0.92

Activations Density 0.010%

accents or special characters

various symbols and special characters

No Comments

No Known Activations