INDEX

Explanations

proper nouns related to political figures, locations, and events

oai_token-act-pair · gpt-3.5-turbo

the prefix "un" indicating negation or reversal

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Ö¼

-0.68

 accur

-0.67

ãĤ¼

-0.66

 Madden

-0.65

 sophistic

-0.63

 defe

-0.63

Peb

-0.62

 abiding

-0.62

ortment

-0.61

 roomm

-0.59

POSITIVE LOGITS

geon

1.31

nel

1.21

geons

1.18

culus

1.12

ned

1.09

idad

1.05

ners

1.03

nels

1.01

iversity

0.98

culosis

0.97

Activations Density 0.036%

proper nouns related to political figures, locations, and events

the prefix "un" indicating negation or reversal

No Comments

No Known Activations