INDEX

Explanations

phrases related to increasing or elevating something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "up"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

cut

-0.67

oth

-0.65

iw

-0.62

Anne

-0.62

ow

-0.61

Eye

-0.60

lean

-0.60

FO

-0.59

oway

-0.59

awed

-0.59

POSITIVE LOGITS

river

0.85

dates

0.83

stairs

0.79

grading

0.79

dating

0.74

raised

0.74

adesh

0.73

 shop

0.72

rights

0.71

grades

0.71

Activations Density 0.111%

phrases related to increasing or elevating something

occurrences of the word "up"

No Comments

No Known Activations