INDEX

Explanations

email addresses

oai_token-act-pair · gpt-3.5-turbo

various isolated characters and symbols from a document

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

IFrame

Link

Negative Logits

 Democracy

-0.71

 refres

-0.70

 Caption

-0.67

 cuts

-0.64

 controls

-0.63

 democracy

-0.60

 retaining

-0.60

 giveaway

-0.60

GGGG

-0.60

 bluff

-0.58

POSITIVE LOGITS

cdn

0.91

#$

0.81

vey

0.80

domain

0.78

omm

0.78

fc

0.77

tm

0.76

jc

0.76

igslist

0.76

fw

0.76

Activations Density 0.073%

email addresses

various isolated characters and symbols from a document

No Known Activations