INDEX

Explanations

terms related to physical proximity or closeness

oai_token-act-pair · gpt-3.5-turbo

mentions of proximity and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ocker

-0.79

err

-0.77

nia

-0.71

tan

-0.69

Merit

-0.69

sb

-0.67

sol

-0.67

tailed

-0.66

stood

-0.65

inn

-0.64

POSITIVE LOGITS

 proximity

1.23

 charms

0.75

 thereto

0.73

 minded

0.72

imity

0.71

 challeng

0.70

 acquaintance

0.70

 unbeliev

0.70

itiz

0.70

 Ascend

0.69

Activations Density 0.008%

terms related to physical proximity or closeness

mentions of proximity and related concepts

No Comments

No Known Activations