INDEX

Explanations

phrases related to being a first in a sequence or category

oai_token-act-pair · gpt-3.5-turbo

mentions of "first" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Machines

-0.74

 Twins

-0.73

 lobb

-0.71

assies

-0.70

Dru

-0.70

 embassies

-0.67

 Vital

-0.66

 Canaver

-0.65

 visuals

-0.64

 segments

-0.64

POSITIVE LOGITS

achable

0.71

cially

0.70

taboola

0.69

clamation

0.69

ailable

0.68

statement

0.67

 contender

0.66

inkle

0.65

 apiece

0.64

 berth

0.64

Activations Density 0.147%

phrases related to being a first in a sequence or category

mentions of "first" in various contexts

No Comments

No Known Activations