INDEX

Explanations

words related to capabilities or skills

oai_token-act-pair · gpt-3.5-turbo

terms related to various aspects of capability and functionality

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

vern

-0.73

 Mast

-0.67

VS

-0.64

ATA

-0.63

actionDate

-0.61

 ellipt

-0.60

 Heart

-0.60

Oak

-0.60

Fri

-0.60

Santa

-0.59

POSITIVE LOGITS

ability

1.46

worthiness

1.10

abilities

1.05

ibility

0.96

BILITY

0.95

jriwal

0.94

ionage

0.93

iqueness

0.92

idth

0.91

ibilities

0.91

Activations Density 0.010%

words related to capabilities or skills

terms related to various aspects of capability and functionality

No Comments

No Known Activations