INDEX

Explanations

political language and references

oai_token-act-pair · gpt-3.5-turbo

repetitive mentions of the word "the."

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

eret

-0.72

venture

-0.71

NB

-0.68

SPONSORED

-0.67

bet

-0.67

ESPN

-0.67

rand

-0.65

Ã©e

-0.64

akeru

-0.64

ea

-0.64

POSITIVE LOGITS

 entirety

1.29

 entire

1.28

 remainder

1.19

 latter

1.09

 possibility

1.06

 same

1.05

 slightest

1.01

 whole

0.99

 aforementioned

0.98

 majority

0.98

Activations Density 0.267%

political language and references

repetitive mentions of the word "the."

No Comments

No Known Activations