INDEX

Explanations

phrases related to reducing or cutting back on something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "cut back" or "step back."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ifix

-0.78

 Representatives

-0.66

urable

-0.65

Jew

-0.64

ision

-0.63

 Motorsport

-0.62

 Newly

-0.60

rification

-0.60

rez

-0.59

Vu

-0.59

POSITIVE LOGITS

packs

0.89

door

0.84

strap

0.82

side

0.81

)=(

0.81

packing

0.80

yards

0.76

country

0.75

stab

0.74

seat

0.74

Activations Density 0.040%

phrases related to reducing or cutting back on something

occurrences of the phrase "cut back" or "step back."

No Comments

No Known Activations