INDEX

Explanations

mentions of locations or directions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "across" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

FORE

-0.71

rw

-0.70

 Anniversary

-0.69

nery

-0.69

lein

-0.68

spot

-0.65

rics

-0.65

gey

-0.65

resy

-0.64

liest

-0.64

POSITIVE LOGITS

 town

0.88

roads

0.82

 rooft

0.77

plain

0.74

 borders

0.73

loading

0.71

outhern

0.68

 aisle

0.67

 Plains

0.66

 Borders

0.66

Activations Density 0.035%

mentions of locations or directions

instances of the word "across" in different contexts

No Comments

No Known Activations