INDEX

Explanations

instances where actions or events are being described

oai_token-act-pair · gpt-3.5-turbo

words related to personal experiences and coping strategies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 tomorrow

-0.94

 earlier

-0.86

 yesterday

-0.85

 tonight

-0.82

 later

-0.75

 beforehand

-0.74

beer

-0.73

 today

-0.71

 Pigs

-0.67

 Sins

-0.65

POSITIVE LOGITS

 steadily

1.05

 progressively

0.92

 relentlessly

0.87

ModLoader

0.77

 tirelessly

0.77

 consistently

0.75

 continuously

0.73

 metic

0.72

Reviewer

0.71

 mathemat

0.70

Activations Density 0.455%

instances where actions or events are being described

words related to personal experiences and coping strategies

No Comments

No Known Activations