INDEX

Explanations

phrases related to potential and possibilities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating potential or possibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ety

-0.80

book

-0.75

minus

-0.75

Reviewed

-0.73

til

-0.72

ele

-0.72

cup

-0.69

 Deadline

-0.68

biz

-0.68

ãĥ¼ãĥ³

-0.67

POSITIVE LOGITS

 misuse

0.91

 future

0.86

 breakthrough

0.86

 unintended

0.84

 fruitful

0.83

 misinterpret

0.81

 leverage

0.81

 advancement

0.80

 enrich

0.79

 redemption

0.79

Activations Density 0.109%

phrases related to potential and possibilities

phrases indicating potential or possibility

No Comments

No Known Activations