INDEX

Explanations

dates and locations

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "was" and related forms, indicating past events or states

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

 IMAGES

-0.81

mare

-0.69

abuse

-0.69

Enlarge

-0.68

 congr

-0.67

#$

-0.66

mares

-0.65

hazard

-0.65

glers

-0.65

 Millions

-0.64

POSITIVE LOGITS

 able

1.04

 regarded

1.01

 also

0.99

 considered

0.95

 awarded

0.93

 distinguished

0.89

 characterized

0.88

 credited

0.88

 married

0.88

 recognised

0.88

Activations Density 0.497%

dates and locations

instances of the verb "was" and related forms, indicating past events or states

No Comments

No Known Activations