INDEX

Explanations

things related to choices or options presented in a list

oai_token-act-pair · gpt-3.5-turbo

mentions of options or choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

grave

-0.75

soever

-0.73

mind

-0.70

hemat

-0.67

urst

-0.67

ritic

-0.66

encers

-0.63

anti

-0.63

friend

-0.60

orks

-0.59

POSITIVE LOGITS

 options

1.10

 option

0.91

 choices

0.86

finder

0.82

atives

0.81

 Options

0.79

nels

0.77

 Option

0.76

izons

0.75

Option

0.73

Activations Density 0.037%

things related to choices or options presented in a list

mentions of options or choices

No Comments

No Known Activations