INDEX

Explanations

phrases indicating causation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "caused" and related contexts

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

 scrimmage

-0.85

aeper

-0.73

ymph

-0.69

istered

-0.69

ault

-0.67

esan

-0.65

iddler

-0.63

 Technique

-0.62

illet

-0.62

CFL

-0.60

POSITIVE LOGITS

 cele

0.91

uria

0.90

 havoc

0.83

 caused

0.77

 cancell

0.77

¿½

0.77

auga

0.75

netflix

0.73

 Causes

0.69

terness

0.69

Activations Density 0.016%

phrases indicating causation

instances of the word "caused" and related contexts

No Comments

No Known Activations