INDEX

Explanations

phrases containing the word "heads", often in the context of conflict or disagreement

oai_token-act-pair · gpt-3.5-turbo

terms related to conflict or disagreement

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

 Agent

-0.70

 agent

-0.70

onda

-0.67

eanor

-0.66

 Slave

-0.65

 Shepherd

-0.64

aed

-0.61

 counselor

-0.61

Ë

-0.61

 slave

-0.60

POSITIVE LOGITS

heads

3.47

birds

1.41

chairs

1.38

Stars

1.30

boys

1.30

Jews

1.29

kies

1.28

dogs

1.27

holes

1.27

casts

1.26

Activations Density 0.034%

phrases containing the word "heads", often in the context of conflict or disagreement

terms related to conflict or disagreement

No Comments

No Known Activations