INDEX

Explanations

phrases related to illicit activities or wrongdoing

oai_token-act-pair · gpt-3.5-turbo

terms related to Silicon Valley and its associated culture

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ©

-0.88

RTX

-0.84

ãĥ³ãĤ¸

-0.83

 guiActiveUnfocused

-0.78

ãĥ¼ãĥĨãĤ£

-0.76

oise

-0.75

ãĥ£

-0.74

ãĥ¼ãĥĨ

-0.71

ilage

-0.68

ãĥĥãĥĪ

-0.68

POSITIVE LOGITS

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.87

terday

0.84

Lens

0.81

Shift

0.81

ÂłÂłÂłÂłÂłÂłÂłÂł

0.75

gged

0.74

Film

0.71

berman

0.71

Else

0.71

ggle

0.70

Activations Density 0.030%

phrases related to illicit activities or wrongdoing

terms related to Silicon Valley and its associated culture

No Comments

No Known Activations