INDEX

Explanations

phrases related to demonstrating one's abilities or worth

oai_token-act-pair · gpt-3.5-turbo

expressions of proving one's worth and ability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 consulted

-0.78

iatus

-0.74

bath

-0.72

cation

-0.72

swer

-0.69

ocument

-0.69

arette

-0.67

monitor

-0.67

mare

-0.67

 Canaver

-0.67

POSITIVE LOGITS

 talents

1.60

 prowess

1.42

 brilliance

1.39

 strengths

1.36

 abilities

1.36

 skills

1.35

 capabilities

1.33

 virtues

1.32

 greatness

1.32

 talent

1.26

Activations Density 0.287%

phrases related to demonstrating one's abilities or worth

expressions of proving one's worth and ability

No Comments

No Known Activations