INDEX

Explanations

information related to historical events or facts

oai_token-act-pair · gpt-3.5-turbo

specific tokens that indicate the passage of time or chronological events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 emoji

-0.87

 Snapchat

-0.82

ðŁ

-0.72

(@

-0.72

 vape

-0.71

ï¸ı

-0.71

 takeaway

-0.70

 ðŁĺ

-0.69

 GoPro

-0.68

 Lyft

-0.68

POSITIVE LOGITS

 postwar

1.01

 Yugoslavia

0.91

0.89

0.88

0.87

 historian

0.87

Activations Density 1.975%

information related to historical events or facts

specific tokens that indicate the passage of time or chronological events

No Comments

No Known Activations