INDEX

Explanations

medical or technical terms related to health issues

oai_token-act-pair · gpt-3.5-turbo

instances of the word "causes" in various contexts related to conditions or effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Zup

-0.75

ischer

-0.72

rez

-0.72

Tweet

-0.68

ivo

-0.66

borg

-0.65

peak

-0.64

ready

-0.63

 preview

-0.63

EY

-0.63

POSITIVE LOGITS

 causes

3.75

 Causes

2.93

 cause

2.42

cause

2.03

 Cause

1.84

Cause

1.69

 cures

1.54

 triggers

1.44

 causing

1.44

 caused

1.44

Activations Density 0.015%

medical or technical terms related to health issues

instances of the word "causes" in various contexts related to conditions or effects

No Comments

No Known Activations