INDEX

Explanations

usernames in various contexts

oai_token-act-pair · gpt-3.5-turbo

terms related to usernames and their context in digital environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

pire

-0.80

 Lumpur

-0.74

erald

-0.71

 leaflets

-0.70

ected

-0.68

arij

-0.65

rams

-0.65

heny

-0.64

gotten

-0.64

emetery

-0.61

POSITIVE LOGITS

 username

1.21

username

1.16

 Username

1.06

\\\\\\\\\\\\\\\\

0.90

filename

0.79

NAME

0.74

\\\\\\\\

0.73

=\"

0.72

Filename

0.72

 surname

0.71

Activations Density 0.009%

usernames in various contexts

terms related to usernames and their context in digital environments

No Comments

No Known Activations