INDEX

Explanations

phrases related to physical violence towards the throat

oai_token-act-pair · gpt-3.5-turbo

references to the throat and related physical actions

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

 BahÃ¡

-0.68

 Logged

-0.68

generated

-0.67

DO

-0.66

INC

-0.66

 âĶ

-0.65

Mod

-0.64

deals

-0.63

imore

-0.63

 Asset

-0.62

POSITIVE LOGITS

 throat

4.06

 throats

3.60

 Thro

1.79

 neck

1.45

 mouth

1.43

 lungs

1.41

 necks

1.39

thro

1.37

 jaws

1.32

 wrists

1.31

Activations Density 0.017%

phrases related to physical violence towards the throat

references to the throat and related physical actions

No Comments

No Known Activations