INDEX

Explanations

terms related to stealing or looting

oai_token-act-pair · gpt-3.5-turbo

terms related to theft and looting

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

 pairing

-0.72

 Evan

-0.69

sen

-0.68

cond

-0.66

 Adelaide

-0.66

uter

-0.65

 Dennis

-0.65

 Connie

-0.65

 Intermediate

-0.65

 Standards

-0.63

POSITIVE LOGITS

 loot

3.78

 looting

3.15

 looted

2.69

 Loot

2.47

 plunder

2.34

 hoard

1.53

 raiding

1.38

spo

1.34

 thieves

1.28

 scaven

1.27

Activations Density 0.013%

terms related to stealing or looting

terms related to theft and looting

No Comments

No Known Activations