INDEX

Explanations

proper nouns or named entities related to world events

oai_token-act-pair · gpt-3.5-turbo

instances of the word "said" in various contexts

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

ï¸

-0.76

ãĥ¼ãĥĨ

-0.72

ographic

-0.72

odox

-0.71

otin

-0.68

odge

-0.66

ä¹

-0.65

clips

-0.64

atown

-0.63

Occup

-0.63

POSITIVE LOGITS

 suppliers

0.76

urances

0.72

 warranties

0.70

 Airways

0.70

 yesterday

0.70

 spokesman

0.69

 spokeswoman

0.68

 troopers

0.67

doms

0.67

 investigators

0.65

Activations Density 0.253%

proper nouns or named entities related to world events

instances of the word "said" in various contexts

No Comments

No Known Activations